Method and system for tracking a position on a material web

Abstract

The present invention relates to a method for tracking positions (w1, w2, w3) on material strips (120, 122, 124) during processing of material strips (120, 122, 124), the method comprising the steps of: a) acquiring first measurement data (300) relating to a first surface region (w1) of the material strip (120) using a first acquisition device (150) at a first time point; b) acquiring second surface regions of the material strip (120, 122, 124) using the first acquisition device (150) at a second time point after the first time point. c) processing material strips (120, 122, 124) in the process steps, d) using a second acquisition device (160) and using the first measurement data and / or the second measurement data (300) to identify a first surface region (s1) on the processed material strip (124), e) using the second acquisition device (160), the first measurement data and / or the second measurement data (300), and the first and second time points to identify a second surface region (s5, s9) on the processed material strip (124).

Description

Technical Field

[0001] The present invention relates to a method and system for tracking the position on a material strip using measurement data about a surface area within the processing range of the material strip. Background Technology

[0002] This system is known from existing technology.

[0003] For example, the article "Integration of Traceability Systems in Battery Production" (Günther Riexinger et al., Procedia CIRP, Vol. 93, 2020, pp. 125-130, ISSN 2212-8271, https: / / doi.org / 10.1016 / j.procir.2020.04.002.(https: / / www.sciencedirect.com / science / article / pii / S221282712030531X)) discloses examples of traceability concepts focusing on identification technologies in battery production. The article introduces the developed traceability concepts and examples of their implementation. For instance, examples include methods for identifying objects or production components by correspondingly tracing inherent object characteristics or applied identification markers.

[0004] The aforementioned drawback of the prior art is that, within the scope of the production process, the known methods still have limitations in terms of the accuracy of identifying the identification location or mark on the product. This is because the production process affects the identification location or mark, and subsequently, the location or mark no longer precisely corresponds to the originally existing identification location or mark. Summary of the Invention

[0005] Therefore, the object of the present invention is to provide a method and / or system by means of which the accuracy of identifying the location and / or markings of a product can be improved within the scope of product manufacturing.

[0006] The objective is achieved by a method having the features of claim 1.

[0007] This method is implemented and configured to track the position on the material strip during processing, and includes the following steps: a. At a first time point, use a first acquisition device to acquire first measurement data related to a first surface region of the material strip. b. At a second time point after the first time point, the first acquisition device is used to acquire second measurement data of the second surface region of the material strip. c. Processing material strips in the process steps. d. Using a second acquisition device and using the first measurement data and / or the second measurement data to identify a first surface area on the processed material strip, e. Using the second acquisition device, the first measurement data and / or the second measurement data, and the first and second time points, identify the second surface region on the processed material strip.

[0008] Here, the use of the first time point and the second time point is implemented and configured such that the first time point and the second time point are used to determine the time interval and / or spatial interval of the first surface region and the second surface region.

[0009] This method, for example, can be implemented and configured as a computer-implemented method. Furthermore, all method steps of this method can be implemented and configured as computer-implemented method steps. It can also be specified that a selection of method steps can be implemented and configured as computer-implemented method steps or computer-aided method steps.

[0010] Furthermore, the method steps mentioned do not necessarily have to be performed sequentially or in a predetermined order. For example, they can be performed partially simultaneously, or in other orders. Additionally, it can be specified that the method steps are performed separately or that other method steps are included.

[0011] The method is also implemented and configured such that acquiring first measurement data of the first surface region according to method step a. and acquiring second measurement data of the second surface region according to method step b. are performed before processing the material strip according to method step c. Here, the method can, for example, be implemented and configured such that acquiring the first measurement data of the first surface region and acquiring the second measurement data of the second surface region are performed from the respective unprocessed material strips.

[0012] Because the identification of surface areas after processing the material strip is improved by using both the acquired measurement data of the corresponding surface areas and the acquisition time of the measurement data in order to identify the surface areas of the material strip in the process steps.

[0013] Therefore, for example, similarity comparisons can be performed using measurement data acquired before and after the process steps. Furthermore, identification can be improved by determining the time intervals and / or spatial intervals between different acquired surface regions using the acquisition time points, and then, based on these intervals, the orientation of potentially identifiable surface regions can be further narrowed down. For example, if the spacing between different surface regions is known before processing, and the first surface region in the surface region has been re-identified after processing, then if the spatial location of the second surface region after processing can be narrowed down based on the known spacing when comparing the measurement data of the second surface region before and after processing, the second surface region in the surface region after processing can be identified significantly more accurately.

[0014] The aforementioned similarity comparisons more frequently produce so-called "false positives." These "false positives" occur when a surface region of a processed material strip is incorrectly identified as another surface region of an unprocessed material strip. The cause of such "false positives" can be, for example, the ambiguity of the visual fingerprint used in this similarity comparison, due to incomplete images (regarding size, resolution, lighting conditions, and noise), and the necessity of using a relatively low recognition threshold to achieve adequate identification of the surface region.

[0015] False alarms can be filtered, for example, by associating the longitudinal position (e.g., in meters) on the strip with each surface region on the strip. The position can be calculated from the timestamps (e.g., a first time point and / or a second time point) of the associated measurement data (e.g., an image) and a meter counter, the latter of which can also be derived from the velocity of the moving electrode strip as an integral over time. Based on the position, the longitudinal spacing between the surface regions can then be calculated, for example.

[0016] Here, the material strip can be made of any possible material, which can be formed, manufactured, and / or processed into a material strip. For example, it can be a material that is accordingly implemented and configured, for example, to be unrolled from and / or wound onto a spool. Typically, it is a very long and relatively thin material strip. Such a material strip can be made of, for example, plastic, metal, fabric, paper, or similar materials.

[0017] Furthermore, it can be specified that the moving material strip moves, for example, along the transport direction, particularly linearly along the transport direction. Furthermore, it can be specified that the moving material strip moves at a transport speed. The transport speed can be, for example, a constant transport speed or a variable transport speed. For this purpose, it can be specified that, for example, at least one speedometer is provided for measuring the speed of the material strip. Furthermore, the speed of the material strip can also be determined using other parameters, such as the rotational speed of the unloading shaft or the winding shaft for the material strip, sometimes together with the corresponding radius of the unloading shaft and / or the winding shaft. Furthermore, other measured values ​​can also be used, by means of which the speed of the moving material strip can be determined in one or another of the above-described ways, or by means of said other measured values.

[0018] Generally, within the scope of this specification, measurement data, i.e., first measurement data and / or second measurement data, can be any type of zero-dimensional, one-dimensional and / or multi-dimensional data structure suitable for similarity comparison and / or re-identification of the data structure.

[0019] In a preferred design, the measurement data can be implemented and configured as two-dimensional image data. Here, the image data can be acquired, or has been acquired, by, an optical acquisition device, such as a camera. Here, the optical acquisition device can be implemented and configured to acquire measurement data within different spectral ranges, such as from the far-infrared to the ultraviolet spectral range, or sub-ranges thereof.

[0020] In addition, the corresponding one-dimensional or multi-dimensional image data may also include temperature data acquired by a thermal imager, or electrical data (such as charge, current, or electric field or field strength) or magnetic data (magnetic field or field strength) acquired by the corresponding measuring device.

[0021] With the help of appropriate measuring equipment, one-dimensional or multi-dimensional, such as two-dimensional, chemical data or surface structure data (e.g., roughness, height profile or height map or similar data) can also be acquired as measurement data.

[0022] The corresponding surface region of the material strip can be any finite two-dimensional region of the material strip. In particular, the surface region can be a continuous region or comprise multiple discontinuous sub-regions. Furthermore, the surface region can be defined, for example, by a regular geometric shape. The surface region can be, for example, rectangular, square, circular, elliptical, or have a similar shape.

[0023] Measurement data acquired separately to identify different surface regions can, for example, be acquired completely over the respective surface region. Furthermore, measurement data acquired regarding a specific surface region can, for example, extend beyond that surface region, overlap with the surface region, or only acquire a portion of the surface region—or a combination of these possibilities.

[0024] Furthermore, the measurement data acquired by the first acquisition device may have an acquired data structure of different size and / or form than the measurement data acquired by the second acquisition device (i.e., different image size and / or image format).

[0025] Here, within the range of acquiring first and second measurement data or other measurement data using the first acquisition device, the same measurement parameters and / or transport speed can be used respectively. Furthermore, different measurement parameters and / or transport speeds can also be used.

[0026] In the same manner, it is also possible to identify the range of the first and / or second surface regions when using the second acquisition device, using the same measurement parameters and / or transport speed respectively, or using different acquisition parameters and / or transport speed.

[0027] Furthermore, when identifying the first and / or second surface regions according to method steps d. and / or e., the same measurement parameters and / or transport speeds as when acquiring the first and / or second measurement data using the first acquisition device can also be used.

[0028] Furthermore, this method can be implemented and configured such that a first time point is also acquired within the scope of acquiring the first measurement data. Similarly, a second time point can be directly acquired within the scope of acquiring the second measurement data. Furthermore, it can be specified that third measurement data different from that acquired by the second acquisition device is acquired within the scope of identifying the first surface region according to method step d., and this third measurement data can, for example, be associated with different third surface regions of the processed material strip. Furthermore, within the scope of acquiring the different third measurement data, the corresponding third acquisition time points of the third measurement data can also be recorded and / or stored together. Within the scope of method step e., the second acquisition device can also acquire different fourth measurement data, which can again be associated with different fourth surface regions of the processed material strip. Here, within the scope of acquiring the different fourth measurement data, the fourth acquisition time points can be recorded and / or stored separately. Here, the different third and / or fourth measurement data and the second acquisition device can be implemented and configured respectively as measurement data or acquisition devices according to this specification.

[0029] Furthermore, when acquiring measurement data according to this specification, other acquisition parameters can be acquired and / or stored separately. Such other acquisition parameters may include, for example, the acquisition time point, acquisition date, acquisition device setting parameters, lighting settings, temperature during acquisition, acquisition angle, acquisition spacing, and / or similar acquisition parameters.

[0030] Here, it can be specified that, when identifying the first surface region according to method step d., in addition to using the first measurement data and / or the second measurement data, other measurement parameters already acquired within the range of acquiring the first and / or second measurement data are also used. Such other measurement parameters can be implemented and configured, for example, according to this specification. Similarly, in identifying the range of the second surface region according to method step e., other measurement parameters can also be used, for example, in addition to the first and / or second measurement data and the first and second time points. These other measurement parameters can also be implemented and configured according to this specification.

[0031] Therefore, for example, the acquisition of the first measurement data can be performed using a first acquisition device and first acquisition parameters, wherein the first acquisition parameters may include, for example, the transport speed of the material belt (e.g., at the time point when the first measurement data is acquired), the first time point at which the first measurement data is acquired, the type and / or model of the first acquisition device, additional information about the acquired measurement data (e.g., image size, data type, physical units of the acquired measurement data, ...), the setting parameters of the first acquisition device, the setting parameters of the acquisition device (e.g., the angle and spacing between the acquisition device and the transport track), lighting parameters, and / or similar acquisition parameters.

[0032] In the same manner, when acquiring second measurement data with the aid of the second acquisition device and when identifying the first surface region using the second acquisition device, the corresponding acquisition parameters can be acquired and / or stored respectively.

[0033] The corresponding acquisition parameters can be generally acquired and / or stored when acquiring all measurement data according to this specification.

[0034] As described above, to acquire the various measurement data mentioned in the method, one or more acquisition devices can be provided, such as cameras or other sensors implemented and configured accordingly, to acquire the corresponding measurement data. Here, the acquisition of one-dimensional or multi-dimensional data structures can be performed, for example, in a single measurement step, such as in a 2D camera, or through a corresponding scan, such as by means of a point sensor or a 1D sensor. In this way, by using a 1D camera oriented perpendicular to the direction of material strip movement (e.g., a so-called line scan camera) and acquiring images while the material strip moves under the line scan camera, it is possible to generate, for example, 2D data structures, i.e., optical images.

[0035] The acquisition device can be implemented and configured as a camera, such as a 3D, 2D, or line scan camera, an RGB or grayscale camera, an infrared or ultraviolet camera, and / or a hyperspectral camera. Furthermore, the acquisition device can be implemented and configured as a height or surface acquisition device.

[0036] Furthermore, the acquisition device according to this specification can be implemented and configured as, for example, a camera (e.g., a hyperspectral line scan camera or an RGB camera), an optical line sensor, an optical sensor, a magnetic sensor, a motion sensor, a position sensor, a material sensor, a touch sensor, and / or any other type of sensor.

[0037] The measurement data described in this specification can be data or data structures (e.g., databases, datasets, 1D data structures or 1D data, 2D data structures or 2D data, 3D data structures or 3D data, or higher-dimensional data or data structures) output from the acquisition device described in this specification and / or transportable or transferable to external devices, such as control devices, edge devices, industrial PCs (IPCs) and / or other computer devices. Such measurement data can be, for example, optical data (e.g., 0D data, 1D data, 2D data (e.g., 2D images), 3D data (e.g., 3D images)), electrical properties or information (e.g., resistance, conductivity, ...), magnetic properties or information, volume measurements, area measurements, state data (e.g., pressure, temperature, ...), motion parameters (e.g., position, velocity, flow rate or velocity, ...), or other measurement data.

[0038] The acquisition device can be implemented and configured as a camera, such as a 3D, 2D, or line scan camera, an RGB or grayscale camera, an infrared or ultraviolet camera, and / or a hyperspectral camera. Furthermore, the acquisition device can be implemented and configured as a height or surface acquisition device. Such a camera can be implemented and configured as a hyperspectral line scan camera, an RGB camera, or an optical line sensor, for example. Additionally, the acquisition device according to this specification can be, for example, an optical sensor, a magnetic sensor, a motion sensor, a position sensor, a material sensor, a touch sensor, and / or any other type of sensor.

[0039] The measurement data described in this specification can be data or data structures (e.g., databases, datasets, 1D data structures or 1D data, 2D data structures or 2D data, 3D data structures or 3D data, or higher-dimensional data or data structures) output from the acquisition device described in this specification and / or transportable or transferable to external devices, such as control devices, edge devices, industrial PCs (IPCs) and / or other computer devices. Such measurement data can be, for example, optical data (e.g., 0D data, 1D data, 2D data (e.g., 2D images), 3D data (e.g., 3D images)), electrical properties or information (e.g., resistance, conductivity, ...), magnetic properties or information, volume measurements, area measurements, state data (e.g., pressure, temperature, ...), motion parameters (e.g., position, velocity, flow rate or velocity, ...), or other measurement data.

[0040] The acquisition of a time point can be performed, for example, by an acquisition device or another time measuring device, such as a corresponding clock, which is synchronized with the acquisition device accordingly. The mentioned time point can be acquired and / or stored, for example, as time or other time signals, such as a counter or similar data, or can be acquired and / or stored.

[0041] The second acquisition device may correspond to the first acquisition device, or it may be the first acquisition device itself. Furthermore, the second acquisition device may have the same measurement principle as the first acquisition device. Additionally, the second acquisition device may be implemented and configured in a manner that is the same as, similar to, or comparable to the first acquisition device, or it may differ from it. Here, the second measurement device can be implemented and configured such that the measurement data acquired by it is comparable to the measurement data acquired by the first acquisition device, making it possible to identify the first surface region according to method step d and to identify the second surface region according to method step e. For this purpose, it may also be necessary to perform appropriate adaptation, normalization, conversion, or similar processing steps on the data after acquiring the first and / or second measurement data, and before performing or being able to perform the aforementioned surface region identification.

[0042] Within the scope of acquiring measurement data using the second acquisition device, for example, the same measurement parameters as when acquiring measurement data using the first acquisition device can be used, or other, adapted, or comparable measurement parameters can be used.

[0043] The process steps can also be any type of method or process step for processing the material strip. This can be, for example, applying material to the material strip, heating, cooling, drying, pressing / calendering, winding, unwinding and / or printing the material strip and / or similar process steps. The process steps according to this specification can also include multiple of the above-described process steps as process sub-steps.

[0044] For example, such material strips are used in the manufacture of batteries and accumulators to produce electrodes for said batteries and accumulators. Here, for example, the electrode material is applied onto a carrier foil, dried, and then pressed (“calendered”). The electrode strip can then be divided into individual material segments for subsequent production steps.

[0045] Since this electrode strip is used in subsequent process steps to manufacture or to manufacture batteries and / or accumulators, it is helpful, or even necessary, to track the manufacturing process of each battery or accumulator by performing positional tracking of the electrode strip used in the manufacturing process across different process steps. The goal is, for example, in the case of defective batteries and / or accumulators, to be able to subsequently trace the cause of the defect. For this purpose, it is advantageous to understand the area of ​​the electrode strip used in the corresponding battery or accumulator and to track it across the multiple production steps. In this way, for example, the cause of the failure can be determined, which provides the possibility of potentially improving the manufacturing process accordingly. Furthermore, with the above information, it is also possible to identify other batteries or accumulators that also have defects or may have defects due to the tracking data.

[0046] In the context of this specification, the term "position resolution" is understood as information that is at least partially and in at least one spatial dimension associated with or provided with positional or orientation information, or is associated with or capable of being associated with positional or orientation information. In the present case, position resolution can be implemented and configured, for example, such that measurement data are at least partially provided with or associated with orientation or positional information in the longitudinal direction of the material strip and / or the transport direction, or that such measurement data are associated with or capable of being associated with such orientation or positional information.

[0047] Another example of processing material strips is printing newspapers and magazines, where colors are applied to the paper web in different process steps, and additional overlays are also possible. In manufacturing roofing strips, for example, different sealing materials are applied to paper or fabric strips, and various other overlay materials are used for reinforcement and setting.

[0048] In these cases, location-based tracking of the corresponding material strips, whether later or during the production process, helps in quality control or fault identification and can significantly improve such measures.

[0049] According to method step d, a first surface region is identified using first measurement data and / or second measurement data, and according to method step e, a second surface region is identified using first measurement data and / or second measurement data. This can be done, for example, such that the similarity between the first measurement data and / or second measurement data and data acquired by the second acquisition device is identified.

[0050] For this purpose, there are numerous technically mature similarity methods for identifying similarities in 2D data structures such as images. Examples of such similarity methods are the so-called fingerprinting methods, namely, so-called “template matching” or “keypoint matching.” An overview of some of these methods can be found, for example, in the article “Integration of Traceability Systems in Battery Production” (Günther Riexinger et al., Procedia CIRP, Vol. 93, 2020, pp. 125-130, ISSN 2212-8271, https: / / doi.org / 10.1016 / j.procir.2020.04.002. (https: / / www.sciencedirect.com / science / article / pii / S221282712030531X)).

[0051] Therefore, for example, according to method step d., identifying the first surface region on the processed material strip can be implemented and configured such that different third measurement data about different third surface regions of the processed material strip are acquired at different third time points using a second acquisition device, and each of the third measurement data is compared with the first measurement data. This comparison can be performed, for example, by means of the similarity method described above.

[0052] Method step d. can be implemented and configured such that a third surface region in a third surface region that has the highest similarity to the first measurement data with respect to the acquired third measurement data is identified and / or re-identified as a first surface region on a processed material strip.

[0053] Method step d. can also be implemented and configured such that, in order to identify the first surface region, the measurement data of each of the acquired third surface regions is compared both with the first measurement data and with the second measurement data. The advantage of this design is that, in cases where the first surface region becomes unrecognizable due to the processing of the material strip through the manufacturing process, and the comparison of the first measurement data with the different third measurement data acquired for different third surface regions fails to identify the first surface region using a preset similarity comparison method or other comparison methods, position tracking can then continue directly with the second surface region. This can be observed by comparing the different third measurement data with the second measurement data, and subsequently identifying the similarity to the second measurement data. It can be concluded that the first measurement data is not identified or is not identified. Subsequently, for example, the third measurement data for the third surface region can be re-recorded, the comparison method or similarity method modified, or other corrective steps can be taken to identify the first measurement data again, for example, on the processed material strip, thereby identifying the first surface region.

[0054] Furthermore, according to method step e, identifying the second surface region on the processed material strip, it is possible to acquire fourth measurement data for the corresponding different fourth surface regions of the processed material strip by the second acquisition device, and the fourth measurement data is verified against the second measurement data by means of a similarity method or a comparison method.

[0055] Furthermore, for example, from the first and second time points acquired in parallel with the acquisition of the first and second measurement data, if the material belt transport speed is known or the speed profile of the transport speed of the moving material belt is known, the distance between the first and second surface regions can be determined within the range of the acquisition of the first and second measurement data.

[0056] Furthermore, it can be specified that, when identifying the first surface region according to method step d., a third acquisition time point is recorded for each acquisition of third measurement data for the corresponding third surface region of the processed material strip. Furthermore, when identifying the second surface region, within the range of acquiring fourth measurement data for the fourth surface region of the processed material strip, a fourth acquisition time point can also be recorded for each acquisition. Now, from the third acquisition time point of the first surface region identified on the processed material strip according to method step d., using the separately acquired fourth time points, the distance between the corresponding fourth surface region and the third surface region that has been identified and / or re-identified as a first surface region on the processed material strip can be determined.

[0057] Based on feature e, the identification of the second surface region can then proceed to determine both the similarity between the acquired fourth measurement data and the second measurement data associated with the second surface region on the unprocessed material strip, and the determination of the distance between the corresponding fourth surface region and the third surface region identified within the range of the first surface region on the processed material strip. As the second surface region of the processed material strip, a surface region is then selected or re-identified from the fourth surface regions, wherein the surface region (within a specific measurement accuracy range) has a certain distance from the identified third surface region, the distance corresponding to the distance between the first and second surface regions of the unprocessed material strip as determined above, and wherein, in parallel, the comparison between the corresponding acquired second measurement data and the fourth measurement data acquired within the range of method step e. shows high similarity, highest similarity, or highest similarity within the measurement accuracy range.

[0058] Here, the aforementioned method of using the spacing between surface regions to identify the second surface region is an example of using a first time point and a second time point within the identification range.

[0059] Another example of using the first and second time points within the scope of identifying the second surface region is, for instance, that the transport speed of the material strip is constant within the scope of the method according to this specification. In this case, the conversion to spatial spacing of the surface regions can be omitted, and for example, within the scope of identifying the second surface region, priority can be given to surface regions in the fourth surface region to which the time interval between the acquisition time of the fourth measurement data and the acquisition time of the third measurement data corresponds to, is close to, or is closest to the time difference between the acquisition time of the second measurement data and the first measurement data.

[0060] If the material conveyor speed is constant during the acquisition of the first and second measurement data, and another material conveyor speed is also constant during the acquisition of the aforementioned third and fourth measurement data, the method can, for example, be designed such that the difference between the third and fourth time points is calculated accordingly based on the known first and second time points and the known mentioned conveyor speeds. After identifying the first surface region on the processed material conveyor according to feature d, the target value of the fourth time point can then be directly determined based on the time difference, wherein, within the range of the second surface region of the processed material conveyor identified according to feature e, it is anticipated that fourth measurement data regarding the corresponding fourth surface region will be acquired.

[0061] In an advantageous design, it can be specified that when identifying the second surface region according to feature e, the separately acquired fourth measurement data for the corresponding fourth surface region are compared only with the second measurement data, and not with the first measurement data. This design can function or be used when the first surface region has already been identified on the material strip within the scope of method step d. Thus, the first surface region and its position on the moving and / or movable material strip are already known, and the first measurement data need not be used again in the method for identifying the second or additional surface regions. In this way, a simplified, improved, and / or accelerated method for identifying the second surface region is obtained, because the identification method is accelerated by reducing the number of comparisons with measurement data.

[0062] In an alternative design, to identify the first and / or second surface regions based on features d. and / or e., special markings on the material strip can also be used, such as printed characters and / or patterns, edge markings, ID information (e.g., QR codes or barcodes), or similar identification features. A comparison method matching these special markings can then be used to identify the first and / or second surface regions based on features d. and / or e.

[0063] Within the scope of this specification, a surface region is generally understood as a specific area on the surface of a movable or mobile material strip. Here, each surface region is associated with and / or may be associated with a physically fixed position on the moving material strip. Here, according to this specification, the names of the first, second, third, and / or fourth surface regions are respectively associated with the corresponding acquired first, second, third, and / or fourth measurement data. As mentioned above, for example, a third or fourth surface region on a processed material strip can also completely or partially correspond to a first or second surface region on an unprocessed material strip, be a part of such a surface region, overlap with or extend beyond said surface region—or a combination of the above.

[0064] In this way, for example, the location defined by the first surface area on the processed material strip can be re-identified on the processed material strip according to method step d, thereby enabling tracking of the material strip within the range of the processing steps.

[0065] Correspondingly, the method explained above can also be extended to the tracking of more than two surface regions. Thus, according to the method explained in this specification, in the case of extending to acquiring measurement data of more than two surface regions of an unprocessed material strip and then subsequently re-identifying the surface regions on a processed material strip, the method mentioned above enables the re-identification and tracking of various precisely defined positions on a moving or movable material strip generated by the process steps.

[0066] In extensions of the described method, it is possible to extend this method to multiple process steps, or even across multiple process steps. Here, it can be specified that, after each process step, the surface areas known before the process step are re-identified or identified using the method according to this specification. It is also possible to specify that, only after a selection of process steps, the previously known surface areas are re-identified or identified using the method according to this specification.

[0067] In this way, an improved and / or simplified method is provided for position tracking or tracing of one or more process steps or the effects of process steps on a moving and / or movable or extended strip of material.

[0068] In the extension of the method, it can also be specified that an additional second surface region is provided on the material strip, and according to method step b, additional second measurement data are obtained for the additional second surface region respectively, and a second acquisition time point is recorded when the corresponding second measurement data is obtained.

[0069] In this case, the identification of the second surface region on the processed material strip based on feature d can be expanded by identifying these additional second surface regions on the processed material strip. Here, the identification of these additional second surface regions can be performed using a second acquisition device, first measurement data, second measurement data, and / or additional second measurement data, as well as first, second, and additional second time points.

[0070] In this way, it is possible to track or trace a material strip extending through process steps with relatively high positional resolution within the range of the process.

[0071] In a favorable design of the aforementioned alternative, it can also be specified that, within the range of identifying the second surface region or another second surface region according to feature e., only the measurement data for which the first, second, and / or other second surface regions have not yet been identified is used. This reduces the computational cost within the identification range according to feature e., thereby further accelerating the method.

[0072] In another alternative, the above method can also be extended to tracking surface areas across multiple process steps.

[0073] In this scenario, after identifying the second surface region on the processed material strip according to feature e, the material strip is processed again in another process step, and then another first surface region on the further processed material strip is identified, similar to feature d. Then, another second surface region on the further processed material strip is identified, similar to method step e. The method can also be extended accordingly to any sequence of process steps.

[0074] In another advantageous approach, it is also possible to combine the above-mentioned method design scheme, the extension of the method to many surface areas and the further extension to many process steps, to obtain tracking of moving or movable material strips across the entire process chain with high positional resolution.

[0075] In a favorable design, it can also be specified that, after successfully identifying the first surface region using the first measurement data according to method step d, the identification of the second surface region is performed using the first time point, the second time point, and the second measurement data according to method step e.

[0076] In another advantageous design, it can generally be stipulated that all measurement data already used to successfully identify surface areas on the processed material strip will no longer be used to identify other surface areas on the processed material strip that have not yet been re-identified. This can be implemented and configured, for example, such that, in order to identify other surface areas on the processed material strip that have not yet been re-identified, only measurement data used for surface areas on the processed material strip that have not yet been identified will be used.

[0077] The aforementioned design improves the efficiency of the method according to this specification because, for surface areas on the processed material strip that still need to be identified, only measurement data is used for which no surface areas have yet been identified on the processed material strip. Because the number of measurement data used in identifying surface areas on the processed material strip is reduced, the method is less resource-intensive in identifying unidentified surface areas of the processed material strip. This makes the method faster and / or more efficient.

[0078] In an advantageous design, it can also be specified that, in method step b, additional second measurement data regarding a second surface region of the material strip is acquired at a corresponding additional second time point using the first acquisition device. This additional second measurement data can then be used, or used for, identifying the first and / or second surface regions within the scope of method steps d and / or e.

[0079] Further development of the design scheme can also specify that, additionally, within the scope of method step e, a second acquisition device, first measurement data, second measurement data and / or additional second measurement data, as well as first, second and additional second time points, are used to identify additional second surface regions.

[0080] In a further improvement, it is possible to specify that the identification of the second surface region and / or the other second surface region is performed using only the measurement data of the first, second and / or other second measurement data of the surface region to which it has not yet been identified on the processed material strip.

[0081] Furthermore, the method according to this specification can be implemented and configured such that the identification of the second surface region according to method step e continues to be performed in the case of measurement uncertainties when determining the first time point and / or the second time point.

[0082] The method can also be advantageously improved such that, in order to identify the second surface region according to method step e., both the similarity between additional fourth measurement data about the additional fourth surface region of the processed material strip obtained in method step e. and the second measurement data obtained according to method step b., and the probability distribution and / or expected distribution of the possible or expected spacing from the first surface region identified according to method step d. to the second surface region to be identified, are used.

[0083] This can be implemented and configured, for example, such that the similarity value to the second measurement data is first associated with each additional fourth measurement data. Furthermore, the space and / or time interval from the first surface region identified according to method step d. is associated with each corresponding additional fourth surface region. This can be done, for example, using the corresponding additional fourth acquisition time point of the associated additional fourth measurement data and the acquisition time of the measurement data associated with the first surface region acquired and identified on the processed material strip by the second acquisition device according to method step d. Then, the spacing probability value is associated with the corresponding previously determined space and / or time interval from the aforementioned spacing probability distribution or desired distribution.

[0084] Subsequently, the following fourth surface region from the additional fourth surface regions is selected as the second surface region identified according to method step e., in which a favorable, maximum, and / or suitable combination of the associated similarity value and the spacing probability value or spacing expectation value of the measurement data is obtained. This can be implemented and configured, for example, such that, according to method step e., the following surface region is identified as the second surface region, in which the sum, sum of squares, sum of absolute values, product, product of squares, and / or product of absolute values ​​of the similarity value and the spacing probability value or spacing expectation value of the measurement data are obtained.

[0085] Taking into account measurement uncertainties when determining the first and / or second time points further improves the method according to this specification, because a more realistic size for the time interval and / or spatial interval of the surface area is taken into account within the scope of identifying the surface area of ​​the processed material strip.

[0086] Therefore, for example, at a preset belt speed of the material belt, specific measurement uncertainties in determining the first time point and / or the second time point result in specific positional ambiguity when calculating the spatial distance between the two surface regions.

[0087] For example, if measurement uncertainties at the first and / or second time points are considered when identifying the second surface region according to method step e, this causes a corresponding uncertainty in the expected spacing between the first and second surface regions of the processed material strip. If a Gaussian distribution or a similar probability distribution is assumed for a measurement time point, the measurement uncertainty mentioned above corresponds, for example, to the half-maximum width of the probability distribution. If a first probability distribution is assumed for the first measurement time point and a second probability distribution is assumed for the second measurement time point, then a probability distribution derived from the two probability distributions is obtained for the expected spacing between the first and second surface regions on the processed material strip, derived from either the time point or the web speed or web speed curve.

[0088] This leads to improved identification of a second surface region on the processed material strip, or a second surface region on the processed material strip and another second surface region. This improved method can be implemented and configured, for example, such that, within the scope of method step e., additional fourth measurement data regarding another fourth surface region of the processed material strip is acquired. Here, the acquired additional fourth time point is associated with each additional fourth measurement data. Furthermore, from the probability distributions of the first and second time points, together with the corresponding transport speeds or transport speed profiles, the probability distribution of the predictable spacing between the first and second surface regions on the processed material strip is determined. Additionally, within the scope of identifying the first surface region on the processed material strip according to method step d., a third time point is recorded, at which third measurement data regarding a third surface region, which is identified as a first surface region on the processed material strip within the scope of method step d., is recorded.

[0089] When comparing the similarity of additional fourth measurement data with the second measurement data within the scope of method step e, the similarity to the second measurement data is recorded for each of the additional fourth measurement data relating to the additional fourth surface regions, and the corresponding similarity value is associated with the additional fourth surface region or measurement data. Furthermore, an additional fourth distance from the identified first surface region on the processed material strip is associated with each of the additional fourth surface regions, the additional fourth distance being derived from the aforementioned third time point and the fourth time point associated with the corresponding fourth measurement data used to acquire the fourth measurement data.

[0090] According to method step e, the identification of the second surface region can be achieved by combining the similarity value of the measurement data determined according to the above description with the probability of the other fourth surface region being a different fourth distance from the already identified first surface region, as explained above, and the probability of the possible distances. Thus, the other fourth surface region can be identified as the second surface region on the processed material strip identified according to method step e, or can be identified as the second surface region, wherein the other fourth surface region obtains the maximum value in the corresponding probability combination of the similarity value and the determined distance.

[0091] Furthermore, the method according to this specification can be implemented and configured such that, within the scope of the process steps of method step c., a change in the length of the material strip occurs between the first surface region and the second surface region, and such that, within the scope of method step e., this change in the length of the material strip is taken into account when identifying the second surface region.

[0092] Here, the method can be implemented and configured such that, within the range of the second surface region identified according to method step e, a possible or expected spacing from the identified first surface region, as specified in this specification, or a spacing probability distribution from the identified first surface region, as specified in the specification, is used. Thus, according to the design of the method, the expected spacing or spacing probability distribution is corrected by the aforementioned length variation: that is, when the length between the first and second surface regions increases, the mentioned possible spacing or the mentioned spacing probability distribution extends corresponding to that length variation. Accordingly, the method is implemented and configured such that when the length between the first and second surface regions decreases, the possible spacing or spacing probability distribution shortens corresponding to that length variation.

[0093] The method of considering the length variation of the material strip when identifying the second surface region according to method step e can also be implemented and configured such that the spacing between the first surface region and the second surface region is no longer considered when identifying the second surface region according to method step e. The method can also be implemented and configured such that, within the scope of method step e, when there is a length variation of the material strip between the first surface region and the second surface region as described above, the first time point and the second time point are no longer considered.

[0094] The design improves the method because it enables reliable, position-resolved tracking of the surface area of ​​the material strip even in cases such as strip breakage, strip repair, or other operations on the material strip.

[0095] Here, the phrase "within the scope of the process steps" is understood to mean that the length change occurs after obtaining the measurement data according to method step b and before identifying the first surface region according to method step d. Alternatively, it can be understood as the length change occurring before, during, and / or after the process steps.

[0096] Here, length variation can be understood as, for example, shortening (e.g., when the strip breaks and is reconnected, or when a specific area is removed) or lengthening the strip by local stretching, or inserting a segment of material at a specific location.

[0097] In another advantageous design of the method according to this specification, it can be specified that, in order to identify the first surface region and the second surface region according to method steps d. and e., modified first measurement data and / or second measurement data are used, wherein the modified first measurement data is generated by applying at least one process ML model to the first measurement data, and the modified second measurement data is generated by applying at least one process ML model to the second measurement data.

[0098] Herein, and particularly within the scope of this specification, the abbreviation “ML” is understood to mean “machine learning” or “Machine Learning”. Machine learning methods, ML models, the term “ML model” and / or the term “process ML model” are further described within the scope of this specification.

[0099] The methods according to this specification can be implemented and configured, for example, such that measurement data regarding a specific surface region characterizes, for example, the appearance, structure, surface relief and / or other surface properties, surface parameters and / or material properties of that surface region. Furthermore, process steps for processing the surface region or material strip can be implemented and configured to, for example, change the surface regarding the aforementioned properties. Here, such changes can be implemented and configured to, for example, alter the surface properties such that comparing measurement data of the surface region before the process step with measurement data acquired after the process step, and re-identifying the surface region after performing the process step, becomes difficult, may be difficult, or even infeasible or impossible.

[0100] Therefore, surface properties can change, for example, by winding a material strip, such as by transferring or being able to transfer the surface structure of adjacent material strip segments on a winding spool to a lower material segment (the structure, for example, can be "imprinted"). For example, the surface properties and / or structure can be changed or can be changed when the material strip is pressed with a pressure roller, when the material strip is coated, or when the material strip is dried.

[0101] Furthermore, when identifying the surface region using the second acquisition device according to method steps d. and / or e., other measurement principles, acquisition parameters, settings, data formats, and / or different measurement settings can be used. Even in this case, such changes make it difficult or even impossible to re-identify the surface region.

[0102] The advantage of the aforementioned design approach, which applies a process ML model to the first measurement data, is that, given the process steps and / or the second acquisition device, the process ML model can be trained, for example, such that by applying the process ML model to the initially recorded measurement data regarding the surface region, the influence of the process steps and / or the second acquisition device on the measurement data regarding the surface region acquired by the second acquisition device can be simulated or partially simulated. Here, the measurement data can, for example, be the first measurement data and / or the second measurement data according to this specification. In this way, changes in the surface region generated by the process steps and / or the second acquisition device can be simulated.

[0103] For example, by using modified measurement data generated by means of a process ML model within the scope of identifying surface regions, such as identifying a first surface region based on feature d and / or identifying a second surface region based on feature e, it is possible to improve the re-identification of the mentioned surface regions by comparing the measurement data obtained from the processed material strip with the aforementioned modified measurement data, or in some cases, this makes re-identification possible.

[0104] For example, a process ML model can be generated for the winding of a strip of material, or the sequential winding and unwinding of strips of material, and can, for example, simulate the transfer of the structure of a region of the strip of material to an adjacent region of the strip on the winding spool, or include such a simulation. Furthermore, a process ML model can also be created for the pressing or calendering of a strip of material, and can, for example, simulate the effect of the surface structure of a particular calender roll on the strip of material through appropriate training, or include such a simulation. The corresponding process ML model can, for example, be generated or can be generated for all process steps according to this specification.

[0105] Furthermore, the process ML model can simulate, or include, the use of a second acquisition device that differs from the first acquisition device. The process ML model can also simulate, or include, the use of measurement parameters and / or measurement arrangements that differ from those acquired using the first acquisition device.

[0106] Within the scope of this specification, the term "measuring arrangement" is understood, for example, as the spatial arrangement and / or installation of the measuring device. Such a spatial arrangement may include, for example, the distance between the acquiring device and the material strip, and the corresponding viewing angle. Furthermore, the measuring arrangement may also include, for example, the type and arrangement of lighting devices, which are used or can be used, for example, within the range of measurement data acquired by the acquiring device.

[0107] The process ML model, for example, can be implemented and configured as an ML model according to this specification.

[0108] The process ML model simulates or partially simulates a specific process step and / or acquires measurement data using specific measurement parameters and / or measurement arrangements with the aid of a specific acquisition device, or includes such simulation, meaning that the simulation is at least a part of the effect of applying the process ML model to the measurement data input therein.

[0109] The process ML model, in particular, is the ML model according to this specification. Here, the process ML model can be implemented and configured such that applying the process ML model to measurement data acquired regarding the surface region of the material strip can simulate, or at least partially simulate, changes in measurement data caused by the influence of specific process steps on the surface region and / or changes in measurement data caused by acquiring the surface region using a second acquisition device, or include such simulations. Here, the simulation of acquiring measurement data using the second acquisition device includes the measurement parameters used and / or the measurement arrangement. Here, the measurement data, the acquisition of the measurement data, the second acquisition device, the surface region, the process steps, and / or the influence of the process steps on the measurement data can be implemented and configured, for example, according to this specification.

[0110] The process ML model, particularly the ML model according to this specification, is implemented and configured such that applying the process ML model to first, second, and possibly other measurement data can simulate, or at least partially simulate, changes in the first, second, and possibly other measurement data due to the effects of process steps on the first, second, and possibly other associated surface areas, or include such simulation.

[0111] In an advantageous embodiment of the invention, the process ML model can be implemented and configured, for example, as a neural network, particularly a deep neural network (DNN).

[0112] Here, machine learning methods are understood, for example, as automated (“machine”) methods that do not produce results through pre-defined rules, but rather (automatically) identify patterns from a number of examples by means of machine learning algorithms or learning methods, and then generate statements about the data to be analyzed based on those patterns.

[0113] This machine learning method can be implemented and configured as a supervised learning method, a semi-supervised learning method, an unsupervised learning method, or a reinforcement learning method.

[0114] Examples of machine learning methods include regression algorithms (such as linear regression), the generation or optimization of decision trees (so-called "Decision Trees"), neural network learning methods, clustering methods (such as so-called "k-means-Clustering"), learning methods or methods for generating support vector machines ("SVM"), learning methods for generating sequential decision models, or learning methods for generating Bayesian models or networks.

[0115] Therefore, an example of a machine learning method is "linear regression." Linear regression is a parametric method where the label is approximated by a weighted sum of all features. In a standard linear model variant, the mean squared error (MSE) is minimized during optimization. There are other linear model variants, which differ depending on the form of the error function. One variant is, for example, the Huber estimator, where, for example, a parameter ε is introduced to eliminate outliers in the input.

[0116] Another example of a machine learning approach is the k-nearest neighbor method. The principle of the k-nearest neighbor (k-NN) model is to determine the k closest neighbors for each input. This is a non-parametric method where the similarity criterion is a defined metric. This metric can be a norm or distance, which can be determined for all inputs. The neighborhood of the label is derived from the neighborhood or similarity of the inputs.

[0117] Decision trees are another example of machine learning (ML) models upon which machine learning methods are built. A decision tree (DT) is a hierarchical structure that allows for nonparametric estimation. When processing data using a decision tree, the input is divided into local regions, the distances between which are defined by a specific metric. These local regions are the decision trees themselves.

[0118] A decision tree is a recursively partitioned sequence of decision nodes and terminal nodes or leaves. At each decision node, a discrete decision is made via a defined function (a so-called discriminant function), the result of which (yes or no) leads to subsequent nodes. If a leaf node is reached, the process ends and an output value is provided.

[0119] The result of applying such machine learning algorithms or learning methods to specific data, particularly in this specification, is referred to as a "Machine-Learning" model or ML model. Here, such an ML model is the digital storage or storable result generated by applying machine learning algorithms or learning methods to analytical data.

[0120] Here, the generation of ML models can be implemented and configured to enable the formation of new ML models by applying machine learning methods, or to modify or adapt existing ML models by applying machine learning methods.

[0121] Examples of such ML models are the results of regression algorithms (e.g., linear regression), neural networks, decision trees, clustering methods (including, for example, the clusters or cluster categories obtained, definitions and / or parameters), support vector machines (SVM), sequential decision models, or Bayesian models or networks.

[0122] Furthermore, different types of ML models can be combined into a single ML model. This model ensemble learning (Ensemble Learning) links different ML models together to achieve better reasoning. The combined ML models form what is called an ensemble. There are several ways to merge models; more precisely, they can be combined through voting, Bagging, or Boosting.

[0123] In addition, there exists so-called automated machine learning. Automated machine learning (AutoML) is a method in which, for a given task or dataset, the algorithm attempts to determine the optimal learning strategy from a characteristic number of machine learning methods or ML models. In AutoML, the algorithm seeks the optimal preprocessing steps and the optimal set of machine learning methods. AutoML can be combined with meta-learning. Meta-learning, also known as "learning to learn," is the process of a system observing how different ML models perform on various learning tasks and then learning from that experience (metadata) to learn knowledge for new tasks much faster than typically can.

[0124] The AUTO-SKLEARN software library (https: / / www.automl.org / automl / auto-sklearn / ) provides a well-implemented version of AutoML. The system can generate a set of up to 15 estimators. Furthermore, it supports up to 14 feature preprocessing methods and 4 dataset preprocessing methods.

[0125] Here, the neural network can be, for example, a so-called "deep neural network," "feedforward neural network," "recurrent neural network," "convolutional neural network," or "autoencoder neural network." Applying the corresponding machine learning method to the neural network is also commonly referred to as "training" the corresponding neural network.

[0126] Decision trees can be implemented and configured, for example, as the so-called "Iterative Dichotomy 3" (ID3), Classification or Regression Tree (CART), or the so-called "Random Forest".

[0127] Specifically within the scope of this specification, an ML model or "Machine-Learning" model is understood as the result of applying machine learning algorithms or learning methods to specific data. Here, an ML model is the digital storage or storable result generated by applying machine learning algorithms or learning methods to analytical data.

[0128] Here, the ML model can exist, be stored, or be storable, for example, in a form that allows the ML model to be applied to new data to generate results. Applying the ML model to data in this way is also called "inference". Furthermore, it can be specified that the ML model is also implemented and configured in its current, stored, or storable form for training the ML model. However, it can also be specified that the ML model is no longer implemented and configured in its current, stored, or storable form for training the ML model; in particular, in this case, the ML model can only be implemented and configured for applying data to generate results, i.e., the aforementioned "inference".

[0129] The data used to create and / or train the ML model according to the invention can be, for example, historical data of the first and / or second acquisition devices or include such data. Furthermore, the data used to create and / or train the ML model can include historical data of acquisition components with the same, similar, or comparable structure to the first and / or second acquisition components, or historical data of components of the same category or type as the first and / or second acquisition components.

[0130] When using an ML model with measurement data from other acquisition components, or when using an ML model with measurement data from other acquisition components, the creation and / or training of such an ML model can also be carried out with the help of historical data of the acquisition components, historical data of comparable acquisition components, or historical data of similar or comparable component types.

[0131] In this way, within the scope of the effect of applying the process ML model to the acquired measurement data, it may not only simulate the effects of process steps, but also additionally simulate the changes to the acquired measurement data caused by the use of different acquisition equipment and / or changes in measurement parameters or measurement arrangements.

[0132] At least in the context of this specification, a neural network is understood to be, for example, an electronic device having a computer program, computer program product, or software—or the computer program, computer program product, or software itself or stored in a storage device—that comprises a network of so-called nodes, wherein typically each node is connected to multiple other nodes. Furthermore, in the context of this specification, a neural network is also understood, for example, as a computer program product or software stored in a storage device that generates such a network according to this specification when run on a computer. A node is also referred to, for example, as a neuron, unit, or cell. Here, each node has at least one input connection and one output connection. The term "input node" is used to describe a neural network node capable of receiving signals (data, sequences, patterns, or the like) from the external world. The term "output node" is understood to describe a node capable of transmitting signals, data, or the like to the external world. The term "hidden node" is understood to be a neural network node that is neither an input node nor an output node.

[0133] Here, the neural network can be implemented and configured, for example, as a so-called deep neural network (DNN). Such a deep neural network is a neural network in which network nodes are arranged in layers (wherein the layers themselves can be one-dimensional, two-dimensional, or higher-dimensional). Here, the deep neural network includes at least one so-called hidden layer, which consists only of nodes that are neither input nor output nodes. That is, the hidden layer is not connected to the input or output signals.

[0134] The term "deep learning" can be understood as, for example, a class of machine learning techniques that utilize many layers of nonlinear information processing for supervised or unsupervised feature extraction and transformation, as well as for pattern analysis and classification.

[0135] Neural networks can also have so-called autoencoder structures. Such autoencoder structures can be adapted to reduce the dimensionality of data, thereby enabling, for example, the identification of similarities and commonalities.

[0136] Neural networks can also be configured as so-called classification networks, which are particularly well-suited for classifying data into categories. Such classification networks can be used, for example, in conjunction with handwriting recognition.

[0137] Another possible structure for neural networks could be a design called a "deep-believe-network".

[0138] Neural networks can also, for example, combine multiple structures described above. Thus, for example, a neural network architecture can include an autoencoder structure to reduce the dimensionality of the input data, and this architecture can then be combined with other network structures to, for example, identify specificities and / or anomalies within the reduced dimensionality of the data, or classify the reduced dimensionality of the data.

[0139] The values ​​describing each node and its connections include other values ​​describing a specific neural network, which can be stored in a value set describing the neural network. Such a value set then represents, for example, a design scheme for the neural network. If such a value set is stored after the neural network has been trained, then, for example, the design scheme of the trained neural network is stored. Therefore, it is feasible, for example, to train the neural network in a first computer system using corresponding training data, then store the corresponding value set associated with the neural network, and transmit it to a second system as a design scheme of the trained neural network.

[0140] Furthermore, software or computer programs that implement neural networks can also be used as design schemes for neural networks. Moreover, variations of such computer programs that are configured for both inference and training of the neural network are possible design schemes for the neural network; variations of such computer programs that are only implemented, configured, and / or optimized for inference in the neural network are also possible design schemes for the neural network.

[0141] Neural networks can typically be trained by inputting data into them and analyzing the corresponding output data from the network using various known learning methods to determine the parameter values ​​of individual nodes or their connections. In this way, neural networks can be trained in a known manner using known data, patterns, sequences, or signals, so that the trained network can then be used, for example, to analyze other data.

[0142] Generally, training a neural network is understood as follows: the data used to train the neural network is processed in the neural network by one or more training algorithms to calculate or change the so-called bias values ​​("Bias"), weight values ​​("weights"), and / or transfer functions ("TransferFunctions") of each node of the neural network or the connection between any two nodes in the neural network.

[0143] To train a neural network, for example, according to this specification, one of the so-called "supervised learning" methods can be used. Here, by training with the aid of appropriate training data, the network is trained to have results or abilities associated with said data. Furthermore, to train a neural network, so-called unsupervised learning methods can also be used. Such algorithms, for example, generate a model for a given input set, which describes the input and makes predictions therefrom. Here, for example, there are clustering methods, which can be used to divide data into different categories when the data can be distinguished from each other by feature patterns.

[0144] When training neural networks, it is also possible to combine supervised and unsupervised learning methods, for example, when one part of the data has trainable properties or capabilities, while another part of the data does not.

[0145] Furthermore, it is also possible to apply so-called reinforcement learning methods, including but not limited to those used for training neural networks.

[0146] For example, training requiring high computing power can be performed on a high-performance system, while further work or data analysis using the trained neural network can be performed entirely on a lower-performance system. Such further work and / or data analysis using the trained neural network can, for example, be performed on edge devices and / or control devices, programmable logic controllers or modular programmable logic controllers, or other appropriate devices according to this specification.

[0147] Monitoring of machine learning and / or machine learning systems works in two main phases: training and inference.

[0148] Inference is the process of generating ML model results by inputting new data into the artifact / model to produce results, and this new data is typically not used to train and / or set up the ML model. For example, machine learning inference is the ability of a machine learning system to make predictions from new data. There are three key components required for machine learning or monitoring inference: a data source, a machine learning or monitoring system for processing the data, and a data target.

[0149] Training involves the process of creating a model using machine learning algorithms. Training includes using deep learning frameworks (such as TensorFlow) and training datasets. IoT data provides a source of training data that data scientists and engineers can use to train machine learning models for a wide range of applications, from fault detection to consumer intelligence.

[0150] Inference involves the process of making predictions using trained machine learning algorithms. IoT data can be used as input to trained machine learning models and enable predictions that control decision-making logic on devices, at edge gateways, or other locations within the IoT system.

[0151] A trained or trained neural network is inherently relatively expensive software. However, the cost of training a neural network is far greater than the cost of using the trained network later. Therefore, it is generally expected that the "burden" of training should be discarded when the trained neural network is later used.

[0152] Although this is a completely new area in computer science, there are two main approaches to taking the massive neural network and modifying it for speed and improved latency in applications.

[0153] The first approach observes the parts of the neural network that are not activated after training. These parts are unnecessary and can be "pruned." The second approach explores the possibility of merging multiple layers of the neural network into a single computational step.

[0154] Furthermore, it can be specified that at least one process ML model is implemented and configured such that the process ML model is applied to the simulation or partial simulation of changes in the first and second measurement data caused by the influence of process steps on the first and second surface regions. or The process step includes multiple process sub-steps, and at least one process ML model is associated with each process sub-step, wherein each process ML model is implemented and configured such that applying the process ML model to the first and second measurement data can simulate or partially simulate the changes in the first and second measurement data caused by the influence of the process sub-step associated with the process ML model on the first and second surface regions.

[0155] When a process ML model is assigned to a single process step, as shown above, it can be specified that at least one process ML model is implemented and configured such that applying the process ML model to measurement data acquired about the surface region prior to the execution of the process step can simulate, or at least partially simulate, the changes in the measurement data generated due to the influence of the process step on the mentioned surface region. The modified measurement data generated by applying the process ML model to the mentioned measurement data can then simplify the identification of the surface region after the execution of the process step, or sometimes even make it possible for the first time.

[0156] Furthermore, it is possible to specify that a process step comprises multiple process sub-steps, but for this purpose, only one process ML model is created for the entire process step consisting of multiple sub-steps. In this case, it is also possible to specify that the process ML model simulates, or at least partially simulates, the impact of the entire process step on the corresponding measurement data, or includes such a simulation.

[0157] In another scenario, where a particular process step comprises multiple process sub-steps, it is possible to specify that a process ML model in at least one of the mentioned process ML models is associated with each of the process sub-steps. Each of the process ML models then simulates the effect of a particular process sub-step on the corresponding measurement data, or includes such a simulation. In a process step comprised of process sub-steps, the modified measurement data throughout the entire process step can then be calculated as follows: Measurement data regarding the surface area of ​​a material strip not yet processed by the process step is acquired. The process ML model of the first process sub-step is then applied to the measurement data. The process ML models of subsequent process sub-steps are then applied to the modified measurement data generated therein to generate further modified measurement data. In this way, the effect of the entire process step on the mentioned surface area is simulated by applying the respective associated process ML models, in the order of the executed process sub-steps. The measurement data obtained after applying the process ML model of the last process sub-step of the process step then corresponds to the modified measurement data according to this specification.

[0158] Applying a process ML model to specific measurement data, including specific simulations, within the scope of this specification means that the effects mentioned by the process ML model are only, or can only be, a part of the overall effects of the process ML model.

[0159] Therefore, for example, the statement "applying a process ML model to specific measurement data can simulate or partially simulate changes in the measurement data resulting from the influence of specific process steps on the surface area associated with the measurement data, or includes such simulation" can mean that applying the process ML model to the measurement data in the manner mentioned above, in addition to the influence of process steps on the measurement data, also simulates the influence of other processes, settings, parameters, acquisition devices, measurement arrangements, or similar factors on the measurement data. Thus, a process ML model can, for example, be implemented and configured such that applying the process ML model to specific measurement data can simulate or partially simulate changes in the measurement data resulting from the influence of process steps on the surface area associated with the measurement data and from other acquisition devices, other measurement parameters, and / or other measurement arrangements.

[0160] Within the scope of this specification, the term "simulation" is understood both as a relatively good approximation or simulation, and as any simulation, even if partial, approximate, or only fundamental, of the impact of process steps on measurement data. Furthermore, the quality of such a simulation can be related to, or at least partially related to, or influenced by, the measurement data itself. Therefore, for individual measurements, applying the specific process ML model according to this specification may result in a relatively good simulation of the process steps' impact on the measurement data, while for other measurements, applying the process ML model may only yield a poor, or even insufficient or unusable, simulation.

[0161] Furthermore, it can be specified that each process ML model in at least one process ML model has been trained using the following methodological steps: Acquire training data from the surface region of the training material strip. The training material strip or its surface area is processed through process steps or related process sub-steps. Obtain the modified training data for the surface region. The process ML model is trained using the training data and the modified training data. Store the trained process ML model.

[0162] Here, the training material strip can be implemented and configured as the material strip according to this specification. The training material strip can also be any material strip within the scope of the corresponding manufacturing process. The term "training material strip" used in the context of describing the training process of the process ML model is for clarity only within the scope of this specification.

[0163] Here, the process ML model for the process steps is applied to the measurement data already acquired about the surface area of ​​the material strip before the application of the process steps, simulating or at least partially simulating the changes in measurement data caused by the influence of the process steps on the surface area, and can be implemented and configured such that the process ML model is trained by the methods described above and / or similar methods.

[0164] Consider, for example, a process ML model for a specific process step, and measurement data acquired about the surface area of ​​the material strip before processing the material strip through the process step. Here, applying the process ML model to the acquired measurement data to simulate, or at least partially simulate, changes in the measurement data caused by the effects of the process step on the surface area, or including such simulation, can be implemented and configured such that the process ML model is trained by the methods described above and / or similar methods according to this specification.

[0165] The process ML model can be implemented and configured as a neural network, such as a deep neural network. In this case, the neural network can be trained or has been trained, for example, using the supervised learning method according to this specification and the training method of this specification.

[0166] In the above-described scenario, for example, the training method according to this specification can be implemented and configured such that training data is input into the ML model or neural network to be trained, and then the neural network to be trained outputs result data. The ML model or neural network is then trained by calculating the deviation between the modified training data and the result data, and the deviation is used to train the ML model or neural network using methods known per se for supervised learning (such as those briefly outlined elsewhere in this specification).

[0167] Furthermore, it can be specified that the acquisition of training data is performed using a first acquisition device or an acquisition device with the same structure as the first acquisition device, along with first measurement parameters and a first measurement arrangement. Furthermore, it can be specified that modified training data is acquired using the same acquisition device, the same measurement parameters, and the same measurement arrangement. In this case, the separately trained process ML models are implemented and configured such that the process ML models are applied to the first measurement data and / or the second measurement data to simulate or partially simulate the changes in the first measurement data and / or the second measurement data caused by the influence of process steps on the first surface region and the second surface region. Specifically, in this case, the separately trained process ML models are implemented and configured such that the process ML models are applied to the first measurement data and / or the second measurement data to simulate only or partially simulate the changes in the first measurement data and / or the second measurement data caused by the influence of process steps on the first surface region and the second surface region.

[0168] Furthermore, it can be specified that the acquisition of training data is performed using a first acquisition device or an acquisition device with the same structure as the first acquisition device, along with the first measurement parameters and the first measurement arrangement. Furthermore, it can be specified that the modified training data is acquired using a second acquisition device or an acquisition device with the same structure as the second acquisition device, employing the second measurement parameters and / or the second measurement arrangement. In this case, the separately trained process ML models are implemented and configured such that applying the process ML models to the first and / or second measurement data not only simulates or partially simulates the changes to the first and / or second measurement data caused by the influence of process steps on the first and second surface regions, but also simulates or partially simulates the changes to the first and / or second measurement data caused by the second acquisition device, the second measurement data, and / or the second measurement arrangement.

[0169] The above objective is also achieved by a system for tracking the position on a moving or movable material strip during processing, wherein the system is implemented and configured to perform the method according to this specification.

[0170] This system includes: - A first acquisition device, which is used to acquire first measurement data and a first time point of a first surface region of a material strip, and the first acquisition device is used to acquire second measurement data and a second time point of a second surface region of a material strip; - A second acquisition device, which is used to acquire measurement data about the surface area of ​​the processed material strip, and the second acquisition device is used to acquire acquisition time points respectively associated with the acquisition of the corresponding surface area; - A calculation unit, implemented and configured to compare acquired measurement data regarding the surface area of ​​the processed material strip with first and / or second measurement data, and to identify the first and / or second surface areas according to method steps d and e of this specification.

[0171] Herein, the movable or movable material strip, the material strip processing and acquisition device, the surface area of ​​the material strip, measurement data, time points, and the identification of the first and / or second surface areas, as well as the comparison of measurement data regarding the surface areas, can be implemented and configured according to this specification.

[0172] The first acquisition device, for example, can be implemented and configured to acquire first measurement data and a first time point for a first surface region of an unprocessed material strip, and second measurement data and a second time point for a second surface region of the unprocessed material strip. This can be implemented and configured, for example, such that the acquisition of the first and second measurement data is performed by means of the first acquisition device during a process step prior to processing the material strip, for example, prior to processing the material strip according to method step c. of this specification.

[0173] Here, the moving or movable material belt can, for example, move along the transport direction at a transport speed and / or along a transport speed profile. For example, the material belt can also move along the direction of motion.

[0174] The system described herein achieves, for example, position-resolved tracking of the effects of the processing on the material strip within the scope of the processing. Here, an objective is to generate, establish, and / or calibrate a coordinate system for the material strip's movement by re-identifying surface regions within the processing area, thereby enabling position-resolved monitoring of the effects of the processing on the material strip. Furthermore, other regions of the material strip can be monitored and / or analyzed through interpolation between different considered surface regions.

[0175] As described above, by implementing and configuring the system mentioned above to perform the methods according to this specification, it is possible to improve or increase the accuracy of identification of surface areas, identification locations and / or markings within the material strip processing range.

[0176] The computing unit can be implemented and configured, for example, as a computer, edge device, PLC, virtual PLC, one or more modules of a PLC or virtual PLC, control device, cloud, automation server, control application in the cloud, or as a comparable computing unit, or include such components. The computing unit can also be implemented and configured as a system consisting of multiple of the above-described components, which can or have been communicatively coupled.

[0177] In the design scheme of the method using one or more process ML models according to this specification, the computing unit may include, for example, the process ML model. Furthermore, it can be specified that the process ML model is set up and built in a sub-device of the computing unit, such as a module for control devices, a separate edge device, the cloud, or another computing unit according to this specification. It can also be specified that the training of such a process ML model is performed either in one of the aforementioned devices or in another computing unit according to this specification. In particular, it can be specified that the training of the process ML model according to this specification is performed in a computing unit with relatively high computing performance, such as a computer, workstation, server, cloud, edge device, or comparable computing unit.

[0178] Here, the computing unit may, for example, have a storage area for storing measurement data, i.e., storing not only the measurement data of the material strip before processing through the process steps but also the measurement data of the material strip after processing through the process steps. Furthermore, the storage area, or another storage area, may also be configured to store acquisition time points, process parameters, and transport speeds. In addition, the computing unit can implement and configure comparisons of the measurement data. This comparison can be performed using comparison methods, fingerprinting methods, or recognition methods known in the prior art. If the measurement data is implemented and configured as image data, then, for example, image comparison methods or image recognition methods known in the prior art can be used.

[0179] A control device can be any type of computer or computer system implemented and configured to control equipment, machines, facilities, instruments, components, or mechanisms. A control device can also be a computer, computer system, or so-called cloud, on which control software or control software applications, such as control applications, are implemented, instantiated, or installed. Such control applications implemented on a computer or in the cloud can, for example, be implemented and configured as one or more applications with programmable logic controller functionality.

[0180] The control device can also be implemented and configured as a so-called edge device, which, for example, can include an application for controlling the equipment or facility. For example, such an application can be implemented and configured as an application with programmable logic controller (PLC) functionality. Here, the edge device can, for example, connect to another control device of the equipment or facility, or connect directly to the equipment or facility to be controlled. Furthermore, the edge device can be implemented and configured such that it is additionally connected to a data network or cloud, or implemented and configured for connecting to a corresponding data network or cloud.

[0181] The control device can also be implemented and configured as a so-called programmable logic controller (SPS) (or PLC). Furthermore, the control device can also be implemented and configured as a so-called modular programmable logic controller (modular SPS).

[0182] Here, the control device can include a control module or a central module, which implements and configures the operation of a control program. For example, the control module can include functions defined by the standard IEC 61131.

[0183] Here, the control module can also be implemented and configured as a software application, for example, to run a control program in real time to control the machined parts. Here, the software application can include, for example, the functions defined in standards IEC 61131 and / or IEC 61499.

[0184] The control module can also be implemented and configured as a separate mechanical module or component, which is implemented and configured to run the control program in real time. Such a mechanical module or component can, for example, include functions defined by standards IEC 61131 and / or IEC 61499. For example, the control module can be implemented and configured as a programmable logic controller itself, or, for example, as a central module of a modular programmable logic controller. Here, the control module can, for example, include the functionality of input-output components, or it may not include the functionality of input-output components.

[0185] A programmable logic controller (SPS) is a component that is programmed and used to regulate or control facilities or machines. Specific functions, such as sequential control, can be implemented in an SPS, enabling the control of input and output signals of a process or machine. Programmable logic controllers are defined, for example, in standards IEC 61131 and / or IEC 61499.

[0186] To connect a programmable logic controller (PLC) to a facility or machine, both actuators, typically connected to the PLC's output, and sensors are used. Status indicators are also used. In principle, the sensor is located at the SPS input, through which the PLC obtains information about what is happening in the facility or machine. Suitable sensors include, for example: light barriers, limit switches, pushbuttons, incremental encoders, level sensors, and temperature sensors. Suitable actuators include, for example: contactors for activating motors, solenoid valves for compressed air or hydraulic pressure, drive control modules, motors, and drivers.

[0187] SPS can be implemented in various ways and methods. That is, it can be implemented as a standalone electronic device, software simulation, a so-called "virtual PLC" or "soft-PLC", a PC plug-in card, etc. Modular solutions are also common, in which SPS consists of multiple plug-in modules. Such modules can be, for example, a central control module, an input-output module, a communication module, a frequency converter module, an application module, or a comparable module.

[0188] A virtual PLC, or so-called Soft-PLC, is understood as a programmable logic controller implemented as a software application and capable of running or currently running on computer equipment, industrial PCs or other PCs, computing devices, or, for example, edge devices. In this context, it is also possible to modularize the virtual PLC or Soft-PLC. Here, the various functions of the programmable logic controller or PLC are designed as individual software modules, which are connected or interoperable via so-called middleware. Such modules can be, for example, a central control software module (e.g., the module includes at least, but is not limited to, features predefined by standard IEC 61131), an Ethernet communication module for connecting to a fieldbus, a specific organization or device, OPC-UA or a comparable communication standard, a web server module, an HMI module (HMI: Human Machine Interface), and / or an application module according to this specification.

[0189] Here, the modular programmable logic controller can be implemented and configured such that it can have multiple modules, typically including, in addition to a so-called central module (also referred to as a control central module or CPU), which is implemented and configured to run control programs, such as to control components, machines, or facilities (or parts thereof), one or more expansion modules. Such expansion modules can be implemented and configured, for example, as current / voltage supply devices, or as input and / or output signals, or as functional modules or application modules to perform specific tasks (e.g., counters, converters, data processing using artificial intelligence methods, including, for example, neural networks or other ML models). In the present case, for example, it can be specified that a process ML model is implemented in such modules for the programmable logic controller.

[0190] For example, functional modules or application modules can also be implemented and configured as AI modules for performing actions using artificial intelligence methods. Such functional modules can, for example, include neural networks or ML models according to this specification, or another ML model according to this specification.

[0191] Edge devices or edge mechanisms can, for example, include applications for controlling devices or facilities. For instance, such applications can be implemented and configured as applications with programmable logic controller (PLC) functionality. Here, the edge device can, for example, connect to another control device of the device or facility, or connect directly to the device or facility to be controlled. Furthermore, the edge device can be implemented and configured such that it is additionally connected to a data network or cloud, or implemented and configured for connecting to a corresponding data network or cloud.

[0192] Edge devices can also implement and configure additional functions related to the control of, for example, machines, equipment, or components (or parts thereof). Such functions could include, for example: - Collect data and transmit it to the cloud and / or perform appropriate preprocessing, compression and / or analysis on such data; - For example, data can be analyzed using AI methods, such as neural networks or corresponding ML models. To this end, edge devices can, for example, include ML models; - Managing or executing the training of neural networks or ML models. Here, the training itself can be performed at least partially on the edge device itself, but may also include, but is not limited to, the cloud. If the training is performed in the cloud, the edge device can, for example, implement and configure for downloading the trained neural network or ML model and subsequently using it.

[0193] The invention will now be illustrated in detail by way of example, using the tracking (so-called “tracking” or “tracing” of production steps or processes) in electrode manufacturing within the scope of battery production.

[0194] In the manufacture of battery cells, the manufacture of battery electrodes is an important step. The electrode manufacture consists of a number of separate, sequential steps in which large rolls of material, known as “foil rolls” (e.g., aluminum or copper strips up to 4 kilometers long), are processed.

[0195] In the coating step, the roll containing the foil is unrolled, coated with an electrode material, also known as a "slurry," and dried. The resulting coated foil, also called an electrode strip, is then wound into a new roll. The resulting roll is then passed to a calendering step, in which the coated foil is pressed between rollers. Here, each step can consist of a sequence of unrolling, processing, and winding the roll.

[0196] In the subsequent longitudinal cutting, the electrode strip is cut into multiple strips of smaller width along the longitudinal direction (length direction). Optionally, additional cutting can also be performed between the cladding and calendering processes.

[0197] The resulting “sub” rolls of coated, calendered, and slit electrode strips are fed to a single-cell assembly unit, where the rolls are cut laterally into plates (e.g., 20 cm in length), stacked, and placed in a container to protect them from environmental impact. Each battery cell consists of multiple electrode plates. While it is easy to identify and trace a single cell as an independent element (e.g., with the aid of printed markings, such as barcodes), it is difficult to identify the origin of the electrode plates across different process steps on a continuous electrode strip.

[0198] Therefore, one of the topics considered in this specification is traceability of electrode strips across all production steps at the board level. For example, consider a scenario where a single cell is identified as defective during final testing. Understanding which segments of the electrode strip comprised the single cell layer is from is crucial for comprehensive root cause analysis and process optimization. However, in today's battery production and / or gigafactories, corresponding tracking and / or traceability are still performed at the slurry batch and reel ID level, allowing only very rough inferences about specific single cells.

[0199] For this type of traceability, it is possible to use markings (e.g., barcodes), printing / laser-engraving the markings onto the foil or applying them to the foil. However, this may raise the following issues: - Marking can impair product quality, (2) - It is difficult to find a suitable location for the markings because most of the uncoated edges of the foil are removed in subsequent processing steps, and the location of the remaining cuts cannot be known in advance. (3) - In addition, the cut serves as a flow collection point, and surface contamination can impair the primary function of the cut.

[0200] Furthermore, this traceability can be achieved by using, at least in part, so-called "visual fingerprinting" to identify and compare images of electrode strips.

[0201] The limitations of this known approach are as follows: it assumes that images of the same strip region from two independent process steps are so similar that they generate the same fingerprint. Otherwise, the accuracy of the comparison deteriorates (mismatch consistency and false alarms).

[0202] For example, the winding and unwinding of the spool alters the optical appearance of the surface. This can particularly affect the beginning sections of the strip, where the spool radius is small, the curvature is high, and the layers on the spool are subjected to pressure from the layers above. For instance, disturbances or prominent structures on the surface can create indentations on adjacent layers of the spool, which subsequently degrade visual legibility.

[0203] The method described in this specification can also be used with visual fingerprints or other fingerprints (in which case the acquisition device is configured as a camera, and the measurement data is therefore the acquired image). Here, for example, a so-called "keypoint scheme" and / or a so-called "template matching scheme" can be followed. In the keypoint scheme, specific keypoints (e.g., specific gray-level non-uniformity) are first detected. Then, the keypoints are described by feature vectors, which are ultimately used to find matching keypoints in the image pair. Existing methods, such as ORB (Oriented BRIEF), keypoint detectors and descriptor extractors, or ASLFeat, can be used for keypoint-based image matching. Alternatively, several schemes exist for template matching, such as those based on the Fast Fourier Transform (FFT) in OpenCV. A less common but known scheme is to adapt only the phase portion of the FFT (ignoring amplitude), which can be advantageous because it focuses only on structural similarity between images and reduces the impact of brightness fluctuations.

[0204] An example of visual fingerprinting based on template matching is... Figure 2 It is shown in the figure and described in detail below.

[0205] The method according to this specification can, for example, have one or more of the following improvements: - Fusion of image-based fingerprint recognition with physical model of the display area - Use a probabilistic model of reasonable consistency (based on distance) to reduce false positive consistency. -Probabilistic modeling using the uncertainty of distance, - Faster search by considering monotonicity constraints.

[0206] Visual fingerprinting, whether using template matching or keypoint descriptors, more frequently produces so-called "false positives." These "false positives" are scan windows of processed material strips that incorrectly match the error windows w of unprocessed material strips (see...). Figure 2 False alarms can be caused by the ambiguity of visual fingerprints, such as due to incomplete images (regarding size, resolution, lighting conditions, and noise), and the necessity of using a relatively low recognition threshold to achieve full recognition of surface areas.

[0207] False alarms can be filtered, for example, by associating the longitudinal position (in meters) on the strip with each window. This position can be calculated from the timestamp of the associated image and a meter counter, the latter also derived from the time-integrated velocity of the moving electrode strip. The longitudinal spacing between windows is then calculated based on the position.

[0208] Unreasonable consistency is consistency whose distance does not correspond to the expected value of other consistencies. The decision on which consistencies are reasonable can be based on a weighted majority vote, where the weights are derived from the confidence level of the consistency (e.g., based on the correlation coefficient). Alternatively, this decision can be made iteratively, for example, using Random Sample Consensus (RANSAC), a known technique in computer vision.

[0209] In another version of this design, the spacing can be expressed as a probability density function, which explicitly describes the uncertainty of the value. For example, the timestamp of a camera image can have an uncertainty of 50 ms. At a line speed of 80 m / min, this means there is an uncertainty of nearly 7 cm in position. Calculating the spacing between two positions further increases the uncertainty. In particular, if the probability density functions of the two positions are described as normal distributions with variances σ_1^2 and σ_2^2, then the spacing between them has a variance of σ_1^2 + σ_2^2, which means that the individual variances are added together. In the case of a typical electrode plate length of, for example, 20 cm, the uncertainty may be large enough to become relevant in the physical model.

[0210] Another (independent) advantage of fusing visual fingerprints with physical sheet models is that monotonicity on the sheet is constrained, and the resulting sequence of images can be used to accelerate alignment. Specifically, this leverages the fact that the position of windows on the sheet monotonically increases. Therefore, instead of comparing each scan window s with all windows w, only a subset of windows w must be considered. For all subsequent consistency, windows w that have already reached a stable consensus on matching scan windows s can be excluded from the window set.

[0211] A special case in this method is tape breakage, i.e., accidental tape breakage, such as due to improper tension control. When repairing a tape breakage, a specific length of the overlay is removed, and the new end is manually spliced. The length of the removed section is usually not recorded, which can affect the spacing between windows. However, if a tape breakage occurs, it is usually recorded / documented at least at the roll level (e.g., for quality control reasons), and its location can usually be roughly estimated from control data. Therefore, in the section surrounding the tape breakage, web-related optimizations can be temporarily disabled.

[0212] Another or alternative modification to known methods can be, for example, to predict process effects (e.g., winding, calendering) via AI-based image transformation models (image-to-image transformation) to improve image consistency across production steps.

[0213] The motivation lies in the fact that the surface of the electrode strip can be altered by methods and / or process steps, such as through winding and / or unwinding. Of course, the surface can also be significantly altered partially through calendering.

[0214] These changes can compromise consistency and accuracy, or even make comparison impossible. For example, for calenders, it might be feasible to circumvent the problem by recording images before calendering, but this would require an additional vision system. However, effects such as those generated by winding and / or unwinding cannot be avoided.

[0215] The basic idea is to train an ML model, such as a deep neural network, according to this specification to predict the effects on the surface. Here, the training set can consist of image pairs from the same region, with and without corresponding effects, and a vector x with additional contextual information (e.g., the position of a partial counter on the strip, product type). An example of creating such training data to model winding and / or unwinding effects could be: acquiring an image recorded before winding and unwinding (e.g., in a coating process, directly after drying and before winding into a roll) and acquiring another image of the same region after unwinding. Another example of modeling calendering effects could be: recording an image before calendering and acquiring another image of the same region after calendering.

[0216] When creating such a training set, using markers (e.g., stickers) can help achieve high accuracy in pixel-level correspondence between images acquired before and after corresponding method steps. Further improving the accuracy of the training set can be achieved by considering pixel-level image offsets to increase the correlation between images acquired before and after corresponding method steps.

[0217] Based on such a training set, it is possible to train a corresponding ML model, such as a deep neural network (DNN), to perform transformations between images with and without processes or process steps. Here, for example, known schemes such as pix2pix can also be used.

[0218] Then, this trained ML model can, for example, as follows: Figure 3 Let's take an example. An image w of the material strip before the process step is fed to the model to predict a transformed image w', which predicts how the original image w will look after the considered process step (e.g., after calendering). Then, w' is used instead of w in the above comparison. The overall scheme is... Figure 3 As shown in the image.

[0219] As used within the scope of this specification, the term "image" generally refers to a 2D image generated by a linear or area array camera that can be produced from a grayscale or RGB image. In principle, an "image" can also be a hyperspectral camera image, or generated through virtual measurements, such as 3D tomography.

[0220] Other advantageous design options are derived in the dependent claims. Attached Figure Description

[0221] The invention will now be further described by way of example with reference to the accompanying drawings.

[0222] Figure 1 An example system is shown for tracking the position of a moving or movable material strip within a range of pressed material strips; Figure 2 Showing according to Figure 1 Exemplary strip segments and exemplary scanning areas of the material strip before and after pressing; Figure 3 An exemplary method flow is shown for comparing images before and after compression using ML transformation of image data before compression. Detailed Implementation

[0223] Figure 1A processing station 140 is shown for pressing material strips 120, 122, and 124. Here, material strips 120, 122, and 124 are unwound from the feed shaft 126 and move at a constant speed v through the pressing station 140 to the take-up shaft 128, where they are rewound after pressing. In the pressing station 140, the material strips are guided between an upper pressure roller 142 and a lower pressure roller 144. Here, the pressure rollers 142 and 144 and the material strips 120, 122, and 124 are arranged, implemented, and configured such that the material strips are pressed or compressed. This pressing step exists, for example, in the production of electrodes for batteries or accumulators, such as after the electrode material is applied to a corresponding carrier layer and dried. In the context of battery electrode production, such a process step is, for example, referred to as "calendering."

[0224] Figure 1 The entire strip of material from the unloading shaft 126 to the winding shaft 128 is not shown. Instead, the same strip of material is shown three times: first as a first image 120 of strip 120 immediately after being unwound from the unloading shaft 126; then as a second image 122 of strip 122 within the pressing range of strips 120, 122, and 124; and then as a third image 124 of strip 124 shortly before winding strips 120, 122, and 124. Here, for ease of explanation, corresponding reference numerals are used both for the corresponding images of the strip of material in the figures and for the corresponding strip of material itself.

[0225] also, Figure 1 The tracking system 110 is shown for tracking the material strip during the material strip processing—for example, for positionally resolving the effect of pressing the material strips 120, 122, 124 by the pressing station 140.

[0226] Here, the tracking system 110 includes a first camera 150 with a first clock 152 (which can also be implemented and configured as a timer, clock, or counter), wherein the first camera 150 and the first clock 152 are implemented and configured such that the clock 152 acquires an acquisition time point 300 for each image 300 acquired by means of the first camera 150, and then stores and / or also stores the time point together with metadata 300, 310 stored for the image 300 as metadata 300, 310 associated with the image 300.

[0227] The tracking system 110 also includes a second camera 160 with a second clock 162 (which can also be implemented and configured as a timer, clock, or counter), wherein the second camera 160 and the second clock 162 are implemented and configured such that the clock 162 acquires the acquisition time point 400 of each image 400 recorded by means of the second camera 160, and then stores the time point together with metadata 400, 410 stored for the image 400 and / or also stores it as metadata 400, 410 associated with the image 400.

[0228] Within the scope of this specification, and particularly in the description of the accompanying drawings, it is assumed that the acquired images 300, 400 are acquired, stored, and / or transmitted together with their respective associated acquisition time points 300, 400. For example, this is not necessarily mentioned separately each time.

[0229] Here, the tracking system 110 includes a computer 170, to which the first camera 150 transmits the images 300 it records along with the corresponding acquisition time points 300. The second camera 160 also transmits the acquired images 400 along with the corresponding acquisition time points 400 to the computer 170.

[0230] Another component of the tracking system 110 is a velocity sensor 130, which is used to acquire the velocities of the material strips 120, 122, and 124 in a time-resolved manner. The velocity data is then transmitted to a computer 170, where it is stored as time-resolved velocity data or a corresponding velocity profile. The computer then implements and configures, for example, processes and / or evaluates the velocity data, i.e., smoothing, averaging, normalization, drift correction, etc. To simplify... Figures 1 to 3 The method flow shown will be explained in the following sections. Figures 1 to 3 In the accompanying drawings and the corresponding method description, it is assumed that the material belt speed v of material belts 120, 122, and 124 is constant.

[0231] Computer 170 is implemented and configured to perform a so-called fingerprinting method, for example, by installing and / or running appropriate software thereon. Here, the fingerprinting system is implemented and configured such that, for example, an image of a specific surface area is acquired before the material strips 120, 122, 124 are processed, and then the surface area is re-identified by comparing an image recorded after the processing of the material strips 120, 122, 124 with a previously recorded image using a fingerprinting method, re-identification method, or identification method known in the art.

[0232] Therefore, for example, images 300 of the material strip 120 before it is pressed by the processing station 140, along with corresponding acquisition time points 300, are recorded at specific time intervals, and then transmitted to the computer 170 along with the acquisition time points 300. Then, after the material strip 122 has been processed by the processing station 140, the second camera 160 records images 400 of the material strip 124 again, along with the corresponding acquisition time points 400, which are then also transmitted to the computer 170.

[0233] Then, computer 170 compares the image 400 acquired by the second camera with the image 300 recorded by the first camera, and attempts to identify, using a fingerprint method (e.g., a method known from the prior art), an image from the image 400 recorded by the second camera 160 that matches the image 300 recorded by the first camera 150. In this way, it is possible to identify and / or compare the same surface areas or locations on the material strips 120, 122, 124 before and after processing, thereby at least partially tracking the effect of processing on the respective surface areas.

[0234] Furthermore, by recording an image 300 of the material strip 120 before processing using the first camera 150, the length scales of the material strips 120, 122, and 124 can be defined. Here, for example, the surface region w1 associated with the first image w1 recorded by the first camera 150 at the first moment after the material strip 120 is released from the feed shaft 126 is set as the zero point of the material strip length scale. From the known transport speed of the material strip and the corresponding acquisition times of the images w1 and w2 recorded by the first camera 150, the spacing between the surface regions w1 and w2 associated with those images w1 and w2 can be determined respectively. In this way, spatial length coordinates on the material strip can be assigned to each corresponding surface region w1 and w2—thus defining length scales, particularly virtual length scales, on the material strips 120, 122, and 124.

[0235] In the same manner, after identifying the first image s1 recorded by the second camera 160, the surface region s1 belonging to that image s1 is again the zero point defined above on the material belt—in this way, the zero point is "found again" or "re-identified" to some extent. By re-identifying the images w1 and w2 recorded by the first camera 150 in the images s1-s9 recorded by the second camera 160, other surface regions s5 and s9 are re-identified accordingly. Then, based on the known transport speed of the material belts 120, 122, and 124 and the corresponding recording time point 400 of the second image 400, the mentioned (virtual) length scale can be reproduced on the material belts 120, 122, and 124 after processing at the processing station 140.

[0236] In this way, for example, it is possible to assign corresponding length coordinates on the material strips 120, 122, 124 to each of the recorded surface areas w1, w2, w3, s1, s5, s9 respectively assigned to the first camera 150 and / or the second camera 160. At least including but not limited to this, it is then possible to immediately track the effect of processing the material strips 120, 122, 124 by the processing station 140 with positional resolution.

[0237] The length coordinates of specific surface areas w1, w2, w3, s1, s5, and s9 remain associated with that surface area throughout the entire preceding and subsequent process chain, until one or more final products are manufactured. Therefore, for example, if a fault or defect occurs in a specific product manufactured using a material strip, it is possible to trace which length coordinates or length coordinate ranges of the material strip were used in the product, and then, based on stored process data and images, to determine the possible causes of the fault or defect.

[0238] Based on the known spatial distance between the first surface region w1 and the subsequent second surface region w2 as described in the above-mentioned specification, the second surface region w2 can be identified after the first surface region w1 has been successfully identified. This can be implemented and configured, for example, such that after identifying the first image w1 or surface region w1 in images s1-s9 recorded by the second camera 160, in order to identify the second surface region w2, an image s5 of the processed material strip 124 is preferentially selected, which has a time interval with the image w1 of the first surface region w1 recorded by the second camera 160. This time interval is derived from the known distance between the surface regions and the transport speed of the material strip.

[0239] For example, if when comparing images s1-s9 of the second surface region w2 recorded by the second camera 160 with the second image w2 recorded by the first camera, images s4, s5, and s6 that are different from the second image w2 recorded by the first camera 150 and have a certain similarity are obtained, then one of the images s5 is selected within the method range, and the distance between the surface region s5 to which the image belongs and the identified first surface region s1 is closest to the expected distance.

[0240] Here, for example, measurement uncertainties in time and width velocity measurements can also be taken into account. Methodologically, this can be considered, for example, such that, in the above case, a spacing probability distribution is determined from the known spacing between the first surface region w1 and the second surface region w2, as well as the measurement uncertainties in image acquisition and material strip velocity measurement. This probability distribution can, for example, be implemented and configured as a Gaussian distribution or a similar probability distribution, or approximated by such a probability distribution. Then, for example, this probability distribution can be used together with a similarity value (derived from comparing images s1-s9 of the second surface region w2 recorded by the second camera 160 with the second image w2 recorded by the first camera 150 according to fingerprint methods known from the prior art) to select the image s5 from the second camera 160 corresponding to the second surface region w2.

[0241] Here, the reference numerals w1, w2, and s1-s9 introduced above are... Figure 2 The scope of the description is detailed in the following section.

[0242] To implement the advantageous design of the fingerprint method described above for identifying surface regions w1 after processing material strips 120, 122, and 124 in processing station 140, computer 170 includes a neural network 172. Here, neural network 170 is configured, designed, and trained such that it simulates the effect of processing material strip 122 in processing station 140 on images w1, w2, and w3 of the unprocessed material strip 120 acquired by first camera 150.

[0243] For this purpose, neural network 172 has been trained with image pairs consisting of images of the surface region recorded by a first camera 150 before pressing and images of the same surface region recorded by a second camera 160 after pressing. Here, neural network 172 is implemented and configured as a deep neural network (DNN) as known in the prior art. The training of neural network 172 is performed according to supervised learning methods known in the prior art for such deep neural networks (DNNs). However, other neural networks or ML models according to the prior art or this specification can also be trained and used for this purpose.

[0244] The improved method thus constructed is then carried out as follows: Images 300 of surface regions w1, w2, w3 recorded by the first camera 150 are input into a neural network 172. The neural network 172 then generates a modified image 330, which is subsequently used for comparison with an image recorded by the second camera 160 after the material strip 124 has been pressed in the processing station 140.

[0245] This improvement in the method increases the probability of identifying the surface regions of the material strips 120, 122, and 124 processed by the processing station in that any possible variations in the surfaces of the material strips 120, 122, and 124 resulting from processing have been simulated and / or incorporated at least in part into the image 300 of the first camera 150 processed by the neural network 172. Such an image 330, generated in this way, may then, in some cases, be more similar to the image 400 recorded by the second camera, representing the corresponding areas, thereby enabling better identification using appropriate fingerprint methods.

[0246] The following text combines Figure 3 This improvement option for the fingerprint method will be further elaborated upon.

[0247] Figure 2 The upper area shows the... Figure 1 The material strip section 120 after the feeding shaft 126 is unfolded is shown.

[0248] Here, the reference numerals for regions w1, w2, and w3 of the material strip segment 120 before processing respectively denote the corresponding surface regions w1, w2, and w3, and also indicate, for example, the composition of these surface regions w1, w2, and w3. Figure 1 The first camera 150 shown in the figure has acquired images w1, w2, and w3. The reference numerals t1, t2, and t3 indicate the corresponding acquisition time points t1, t2, and t3 of the images w1, w2, and w3, for example, acquired by the first camera 150.

[0249] also, Figure 2 The same material strip segment 124 as the upper segment is shown in the middle and lower regions, respectively, but this time it is after processing the material strip segment 122, or just after winding. Figure 1 Before the reel 128 shown.

[0250] exist Figure 2 In the middle, the arrow 'v' symbolizes... Figure 2 The material strip segments 120 and 124 shown move at a speed v in the direction of the arrow. Therefore, at the camera relative to... Figure 2 When stationary, material strip segments 120 and 124 move through the camera in the direction of the arrows shown.

[0251] Here, the reference numerals for regions s1, s2, s3, s4, s5, s6, s7, s8, and s9 (also abbreviated as s1-s9 in this specification) of the processed material strip segment 124 respectively represent the corresponding surface regions s1, s2, s3, s4, s5, s6, s7, s8, and s9 (abbreviated as s1-s9), and also indicate the composition of these surface regions s1, s2, s3, s4, s5, s6, s7, s8, and s9 (s1-s9). Figure 1The images s1, s2, s3, s4, s5, s6, s7, s8, and s9 (s1-s9) acquired by the second camera 160 are shown. The reference numerals T1, T2, T3, T4, T5, T6, T7, T8, and T9 (T1-T9) indicate the corresponding acquisition times T1, T2, T3, T4, T5, T6, T7, T8, and T9 (T1-T9) of the images s1, s2, s3, s4, s5, s6, s7, s8, and s9 (s1-s9) by the second camera 160.

[0252] Figure 2 The upper area of ​​the middle shows Figure 1 The material strip 120 shown is in the area immediately after being unwound from the feed shaft 130 and before processing in the processing station 140. Here, a first surface region w1 is shown on the left side of the material strip 120, a second surface region w2 is shown in the middle, and a third surface region w3 is shown on the right side.

[0253] exist Figure 2 In the process, characteristic shading lines are assigned to the corresponding surface regions w1, w2, w3 of the unprocessed material strip 120. These shading lines characterize both the specific appearance of the corresponding surface regions w1, w2, w3 and the images w1, w2, w3 obtained therefrom.

[0254] Figure 2 At the bottom is a length scale, which shows the length coordinates of the regions 120 and 124 along the material strip. Based on this length scale, Figure 2 As shown: along the material strip segments 120 and 124, the first surface region w1 has a starting coordinate x1, the second surface region w2 has a starting coordinate x3, and the third surface region w3 has a length coordinate x5.

[0255] Now, before the material strip segment 120 undergoes process treatment in the processing station 140, at time point t1, by Figure 1 The first camera 150 shown acquires an image w1 of the first surface region w1. At time t2, an image w2 of the second surface region w2 is acquired in the same manner. In the same manner, at time t3, the first camera 150 acquires an image w3 of the third surface region w3 from the third surface region w3.

[0256] The distance between the first surface region w1 and the second surface region w2 can be calculated, for example, from the difference between the acquisition time t2 of the image w2 of the second surface region w2 and the acquisition time t1 of the image w1 of the first surface region w1, and the transport speed v of the material strip segment 120. In this way, the starting coordinate x3 of the second surface region w2 can be calculated from the known position coordinate x1 of the first surface region w1. Similarly, the starting coordinate x5 of the third surface region w3 can then be determined from the acquisition time t3 of the image w3 of the third surface region w3, the acquisition time t2 of the image w2 of the previous surface region w2, and the transport speed v of the material strip segment 120.

[0257] To simplify the following description, it is assumed that the material strip moves at a constant speed v throughout the entire scope of the method described in this specification.

[0258] Therefore, it is known, based on the above explanation, that after acquiring the image w1 of the first surface region w1, a time t2-t1 elapses before acquiring the image w2 of the second surface region w2 is performed. The distance x3-x1 between the second surface region w2 and the first surface region w1 is also known. Furthermore, it is also known that after acquiring the image w2 of the second surface region w2, a time t3-t2 elapses before acquiring the image w3 of the third surface region w3 is performed. Here, the distance x5-x3 between the third surface region w3 and the second surface region w2 is also known.

[0259] according to Figure 2 The processed material strip segment 124 shown in the middle area is described below as a first variant of a tracking method for identifying or re-identifying the surface regions w1, w2, w3 as explained above on the material strip segment 124 that has undergone processing in the processing station 140.

[0260] Here, by the relevant Figure 1 The second camera 160 mentioned above records images of the associated surface regions s1-s9 on the processed material strip segment 124 at corresponding recording time points T1-T9.

[0261] Typically, images s1-s9 of the processed material strip segment 124 are then compared with images w1, w2, and w3 of the unprocessed material strip segment 120 using a fingerprinting method according to existing technology. The second camera 160 records images in a different image format than the first camera 150. Therefore, in Figure 2 In the view, the images s1-s9 recorded by the second camera have a different image format than the images w1, w2, w3 recorded by the first camera 150.

[0262] The result of the comparison is Figure 2 The processed material strip 124 is symbolically represented by the corresponding shaded lines of the corresponding images s1-s9. Therefore, for example, the consistent shaded lines of the first surface region s1 and the seventh surface region s7 of the processed material strip 124, or the consistent shaded lines of the first s1 and the seventh image s7 of the surface regions s1 and s7, indicate that these two images s1 and s7 have a similarity to image w1 of the first surface region w1 of the unprocessed material strip 120. The same applies to the similarity between the fifth image s5 and the eighth image s8 of the processed material strip 124 and image w2 of the second surface region w2 of the unprocessed material strip 120; and also to the similarity between the third image s3 and the ninth image s9 of the processed material strip 124 and image w3 of the third surface region w3 of the unprocessed material strip 120. This applies to the processed material strip 124... Figure 2 In the surface areas s2, s4, and s6 without shaded lines, no similarity was found to images w1, w2, and w3 used for comparison with the unprocessed material strip 120.

[0263] Therefore, in the first step, using a fingerprinting method according to the prior art, images s1-s9 of the processed material strip 124 are now compared with image w1 of the first surface region w1 of the unprocessed material strip 120. Here, it is confirmed that image w1 of the first surface region w1 of the unprocessed material strip 120 is similar to image s1 acquired at time point T1 and image s7 acquired at time point T7 of the processed material strip 124. Furthermore, it is known that the first surface region w1 on the unprocessed material strip 120 and... Figure 2 The spacing of the previously observed surface regions is not shown. By comparing the acquisition time points T1 and T7 with this known spacing, taking into account the transport speed v, only the surface region s1 of the processed material strip 124 acquired through the first image s1 can correspond to the first surface region w1 of the unprocessed material strip 120. From the corresponding acquisition time point T1, Figure 2 Based on the acquisition time of the previous images (not shown) and the transport speed v of the material strips 120, 122, and 124, it is now possible to determine the position coordinate x2 of the surface region s1 on the processed material strip 124, which corresponds to the first surface region w1 on the unprocessed material strip 120.

[0264] In the second step, images s1-s9 of the processed material strip 124 are now compared with image w2 of the second surface region w2 of the unprocessed material strip 120. Here, it is confirmed that image w2 of the second surface region w2 of the unprocessed material strip 120 is similar to images s5 acquired at time point T5 and s8 acquired at time point T8 of the processed material strip 124. Furthermore, it is known that the distance between the second surface region w2 on the unprocessed material strip 120 and the previous first surface region w1 is significant. By comparing the acquisition times T5 and T7 with this known distance, taking into account the transport speed v, only the surface region s5 of the processed material strip 124, acquired through the fifth image s5, can correspond to the second surface region w2 of the unprocessed material strip 120. From the acquisition time point T5, the acquisition time point T1 of image s1, and the transport speed v of material strips 120, 122, and 124, it is now possible to determine the position coordinate x4 of the surface region s5 on the processed material strip 124 that corresponds to the second surface region w2 on the unprocessed material strip 120.

[0265] Similarly, it is then determined that the surface region s9 of the processed material strip 124, acquired through the ninth image s9, corresponds to the third surface region w3 of the unprocessed material strip 120. In the same manner, the position coordinate x6 of the surface region s9 on the processed material strip 124 corresponding to the third surface region w3 on the unprocessed material strip 120 can also be determined.

[0266] according to Figure 2 The pressed material strip segment 124 shown below is another variation of the above-described tracking method described below, which is used to identify or re-identify the surface regions w1, w2, w3 described above on the pressed material strip segment 124 in the processing station 140.

[0267] Unlike the method described above, here the images s1-s9 of the processed material strip 124 are compared only with the images w1, w2, w3 of the unprocessed material strip 120 that have not yet been identified by the previous comparison steps.

[0268] This is Figure 2 As shown in the figure, such that with Figure 2 Compared to the example shown in the middle, in Figure 2 Some of the surface regions s1-s9 shown in the lower part no longer have shaded lines. This is because the images w1, w2, w3 of the identified surface regions w1, w2, w3 of the unprocessed material strip 120 corresponding to the shaded lines are no longer used for comparison with the images s1-s9 of the processed material strip 124.

[0269] Therefore, for example, in order to examine the second to ninth images s2-s9 of the processed material strip 124, only images w2 and w3 of the second and third surface regions w2 and w3 of the unprocessed material strip 120 are used. The reason is that the first surface region w1 of the unprocessed material strip 120 has indeed been identified or recognized on the processed material strip, and therefore the corresponding structure cannot reappear in the subsequent images s2-s9 of the processed material strip.

[0270] Furthermore, in order to examine the sixth to ninth images s6-s9 of the processed material strip 124, for example, only image w3 of the third surface region w3 of the unprocessed material strip 120 is used. This is because the first and second surface regions w1 and w2 of the unprocessed material strip 120 have indeed been identified or recognized, and the corresponding structures will not appear in subsequent images s6-s9.

[0271] exist Figure 2 In this context, it is possible to identify, for example, the seventh and eighth images s7 and s8. Figure 2 The lower region no longer has a shaded line, while the corresponding images s7 and s8 are in... Figure 2 The central region still contains a shaded line. This is because, during the examination of images 7 and 8 (s7 and s8), the first and second surface regions w1 and w2 of the unprocessed material strip were already identified. Therefore, to subsequently examine surface regions s6-s9, only image w3 of the third surface region w3 of the unprocessed material strip 120 is used. Furthermore, when examining, for example, the processed material strip 124 in the aforementioned seventh and eighth images s7 and s8 using this image, no similarity was identified.

[0272] Figure 3 An example of a method flow or method structure for another advantageous design scheme of the identification method mentioned above is shown.

[0273] Here, we use what has already been discussed Figure 1 The neural network 172 shown in computer 170 is used to consider, approximate or simulate—or at least partially simulate or approximate—the effects of processed material strips 120, 122, 124 on images w1, w2, w3 recorded on surface regions w1, w2, w3 of unprocessed material strips 120.

[0274] As described above, the neural network 172 has been trained for this purpose using a training method known from the prior art for supervised learning with the aid of images, which consist of images of a specific surface region recorded by a first camera 150 before pressing and images of the same surface region recorded by a second camera 160 after pressing. Furthermore, the neural network 172 is implemented and configured as a "deep neural network" (DNN).

[0275] In the aforementioned advantageous design, the neural network 172, and also, for example, each ML model 172 according to this specification, can additionally be implemented and configured such that the aforementioned image pairs are created using different process conditions, i.e., process parameters, measurement positions, material strip speeds, temperatures, and / or product characteristics. Furthermore, the aforementioned process conditions, or portions thereof, can also be, or have been, part of the training data. Here, the neural network 172, or each ML model 172 according to this specification, can also be implemented and configured such that, in addition to the corresponding image data, the process conditions according to this specification regarding the material strip process steps are used as input data to the neural network 172 or ML model 172.

[0276] exist Figure 3 The left-hand region illustrates an optional extended method flow within the image acquisition range of the unprocessed material strip 120, such as its combination, for example. Figure 1 and / or Figure 2 The following explanation is provided. The method flow shown here is an example of a possible extended design scheme of method steps a. and / or b. according to this specification. Here, in the first method step 300, one or more images w are acquired from the unprocessed material strip 120, along with the acquisition time points of the corresponding images w. In parallel with this, and / or after or before, in another method step 310, process data is determined, i.e., for example, process data regarding process steps, camera position, surface area position or similar position, material strip speed and / or product identification.

[0277] Using the aforementioned neural network 172, in the next method step 320, the neural network 172 is used to perform image transformation on the image w acquired in the first method step 300. Here, the image data of the acquired image w, and at least optionally the aforementioned process data, and possibly also the acquired time points, are input into the neural network 172 as input data.

[0278] As output data of neural network 172, a transformed image w' is then obtained, which simulates the effect of process steps on the previously acquired image w of the unprocessed material strip 120. The transformed image w', along with its corresponding acquisition time point and, if necessary, the mentioned process conditions, is then stored in a data storage device 340, such as computer 170, another computer, or a corresponding storage device 340.

[0279] Figure 3 The right-hand area is shown in accordance with Figure 1Another data acquisition step after processing material belt 124 via processing station 140. The method flow shown here is, for example, a design example of a portion of method steps d. and / or e. according to this specification. Here, again by means of Figure 1 The second camera 160 shown acquires images s and their corresponding acquisition timestamps from the processed material strip 124 in method step 400. Furthermore, in method step 410, the corresponding process data processed through the processing station is acquired and / or stored again. These images and acquisition timestamps can then be stored in a suitable storage device or stored therein (not in...). Figure 3 (As shown in the image).

[0280] exist Figure 3 In another method step 460 shown below, the converted image w' from the unprocessed material strip 120, stored in data memory 340, is then compared with the image s acquired from the processed material strip 124. This comparison can be performed, for example, by fingerprint recognition or similar known identification methods, as explained in the foregoing specification. The method flow shown in this context is also an example of a design scheme, for example, as part of method steps d. and / or e. according to this specification.

[0281] Furthermore, in method step 450, a physical model of the material strip is used to identify the image w' recorded and converted from the unprocessed material strip 120 by means of the images es acquired from the processed material strip 124. Here, for example, the known locations and spacing of the surface regions acquired on the unprocessed material strip 120 are used to better identify the surface regions on the processed material strip 124. This method can also be implemented and configured, for example, according to this specification.

[0282] Therefore, as a result of this matching or comparison according to method step 460, taking physical model 450 into account, the surface area recorded on the unprocessed material strip 120 is positioned on the processed material strip 124. This positioning can also be implemented and configured, for example, according to this specification.

[0283] The matching or comparison step can be, for example, an example of a part of method steps d. and / or e. according to this specification.

Claims

1. A method for tracking positions (w1, w2, w3) on material strips (120, 122, 124) during processing of the material strips (120, 122, 124), the method comprising the steps of: a. At a first time point, first measurement data (300) relating to the first surface region (w1) of the material strip (120) is acquired using a first acquisition device (150). b. At a second time point after the first time point, the first acquisition device (150) is used to acquire second measurement data relating to the second surface regions (w2, w3) of the material strips (120, 122, 124). c. Process the material strips (120, 122, 124) in the process steps. d. Using the second acquisition device (160) and the first measurement data and / or the second measurement data (300), the first surface region (s1) on the processed material strip (124) is identified. e. Using the second acquisition device (160), the first measurement data and / or the second measurement data (300), and the time interval and / or spatial interval between the first surface region and the second surface region determined by the first time point and the second time point, identify the second surface region (s5, s9) on the processed material strip (124).

2. The method according to claim 1, characterized in that, After successfully identifying the first surface region (s1) using the first measurement data (300) according to method step d, the second surface region (s5, s9) is identified according to method step e using the first time point, the second time point, and the second measurement data.

3. The method according to any one of the preceding claims, characterized in that, The identification of the second surface region (s5, s9) is also performed according to method step e, using measurement uncertainties used to determine the first time point and / or the second time point.

4. The method according to any one of the preceding claims, characterized in that, During the process step in method c., the length of the material strip (120, 122, 124) between the first surface region (w1) and the second surface region (w2, w3) changes, and During method step e, the length variation of the material strip is taken into account when identifying the second surface region (s5, s9).

5. The method according to any one of the preceding claims, characterized in that, In order to identify the first surface region and the second surface region (s1, s5, s9) according to method steps d. and e., modified first measurement data (300) and / or second measurement data are used, wherein the modified first measurement data is generated by applying at least one process ML model (172) to the first measurement data (300), and the modified second measurement data is generated by applying at least one of the process ML models (172) to the second measurement data.

6. The method according to claim 5, characterized in that, At least one of the process ML models (172) is implemented and configured such that the process ML model (172) is used for application simulation or partial simulation of changes in the first measurement data (300) and the second measurement data caused by the effects of the process steps on the first surface region (w1) and the second surface region (w2, w3), or the process ML model includes such simulation. or, The process steps include multiple process sub-steps, and each process sub-step is assigned at least one process ML model in the process ML model (172). Each process ML model is implemented and configured such that the process ML model is used for application simulation of the first measurement data (300) and the second measurement data, or to partially simulate the changes in the first measurement data (300) and the second measurement data caused by the influence of the process sub-step assigned the process ML model on the first surface region (w1) and the second surface region (w2, w3), or the process ML model includes such simulation.

7. The method according to claim 5 or 6, characterized in that, At least one of the process ML models has been trained using the following method steps: Acquire training data (300) related to the surface region (w1) of the training material band (120, 122, 124). The training material strip (120, 122, 124) or the surface area (w1) of the training material strip is processed through the process steps or associated process sub-steps. Obtain modified training data (400) related to the surface region (s1). The process ML model (172) is trained using the training data (300) and the modified training data (400). Store the trained process ML model (172).

8. A system (110) for tracking positions (w1, w2, w3) on material strips (120, 122, 124) during processing of the material strips (120, 122, 124), wherein, The system (110) is implemented and configured to perform the method according to any one of the preceding claims, the system comprising: A first acquisition device (150) is configured to acquire first measurement data (300) relating to a first surface region (w1) of the unprocessed material strip (120) and record a first time point, and the first acquisition device is configured to acquire second measurement data relating to a second surface region (w2, w3) of the unprocessed material strip (120) and record a second time point. A second acquisition device (160) is used to acquire measurement data (400) related to the surface areas (s1-s9) of the processed material strip (124), and the second acquisition device is used to record the acquisition time points associated with the corresponding acquisition of the surface areas (s1-s9). A calculation unit (170) is implemented and configured to compare acquired measurement data (400) related to surface regions (s1-s9) of the processed material strip (124) with the first measurement data and / or the second measurement data (300), and the calculation unit is configured to identify the first surface region and / or the second surface region (s1, s5, s9) according to method steps d. and e. of the method described in the preceding claims.

Images